Method and system for monitoring and analyzing environmental temperature and humidity of underground powerhouse of hydropower station

Abstract

The invention discloses a hydropower station underground powerhouse environment temperature and humidity monitoring and analysis method and system, and relates to the technical field of temperature and humidity monitoring, and the method comprises the steps: collecting temperature and humidity data in an underground powerhouse in real time, carrying out the preprocessing, transmitting the data to a central processing unit through a wireless transmission technology and an encryption communication protocol, and transmitting the data to the central processing unit; establishing a multi-parameter correlation model, performing correlation analysis on the preprocessed temperature and humidity data, equipment operation data and personnel activity data, automatically adjusting ventilation and dehumidification equipment according to a correlation analysis result, intelligently regulating and controlling the temperature and humidity of the environment, and starting a disaster early warning and emergency response mechanism when monitoring that the environment is abnormal. And residual energy generated in operation of the environment control equipment is recovered to a power grid through energy feedback. A plurality of sensors and an energy recovery mechanism are arranged, and the problems that in the prior art, data transmission is lack of safety, regulation and control are not timely, and energy is wasted are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature and humidity monitoring, and in particular to a method and system for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station. Background Art

[0002] The four hydropower stations built and managed by the company in the Huoxi River Basin of the Fujiang River are all diversion-type hydropower stations with an installed capacity of 400MW. The main power plants of the power plants are all underground plants. When the temperature difference between the medium and the ambient temperature is large, the moisture in the air will precipitate from the metal pipes and equipment in the plant, forming condensed water on the surface of the equipment or pipes, causing corrosion of the metal pipes and equipment and a humid environment, which affects the service life of the equipment.

[0003] The existing related technologies have deficiencies in environmental monitoring and data transmission. First, the existing monitoring systems often lack preprocessing of environmental data, resulting in low quality of data transmitted to the central processor, which affects the accuracy of subsequent analysis. Secondly, the existing technology lacks effective encryption measures in the data transmission process, which is easy to cause data leakage and bring hidden dangers to the safe operation of the hydropower station. In addition, the existing system lacks intelligence and automation in environmental control, and cannot perform predictive maintenance and fault diagnosis based on real-time data and equipment operating status, nor can it promptly activate disaster warning and emergency response mechanisms when the environment is abnormal. Therefore, the present invention aims to provide a method and system for monitoring and analyzing the environmental temperature and humidity of the underground powerhouse of a hydropower station, so as to solve the above-mentioned technical problems and improve the efficiency and safety of environmental monitoring and control.

[0004] The present invention collects temperature and humidity data in the underground powerhouse in real time, performs preprocessing, and uses wireless transmission technology and encrypted communication protocols to ensure efficient and secure data transmission. At the same time, a multi-parameter correlation model is established to correlate and analyze the preprocessed temperature and humidity data with equipment operation data and personnel activity data, thereby realizing intelligent control of the environment. Based on real-time data and equipment operation status, the present invention also implements predictive maintenance and fault diagnosis, as well as disaster warning and emergency response mechanisms, thereby greatly improving the intelligence level and emergency response capabilities of the underground powerhouse environment control of the hydropower station. Summary of the invention

[0005] In view of the above existing problems, the present invention provides a method and system for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station, so as to solve the problems of lack of security in data transmission, untimely regulation and energy waste in the prior art.

[0006] In order to solve the above technical problems, a method for monitoring and analyzing the temperature and humidity of the underground powerhouse of a hydropower station is proposed, including:

[0007] The temperature and humidity data in the underground plant are collected in real time and preprocessed, and the data is transmitted to the central processor through wireless transmission technology and encrypted communication protocol; a multi-parameter correlation model is established to correlate and analyze the preprocessed temperature and humidity data with equipment operation data and personnel activity data. According to the correlation analysis results, the ventilation and dehumidification equipment are automatically adjusted to intelligently control the temperature and humidity of the environment; predictive maintenance and fault diagnosis are implemented based on real-time data and equipment operation status. When environmental abnormalities are detected, the disaster warning and emergency response mechanism is activated, and the surplus energy generated during the operation of the environmental control equipment is recovered to the power grid through energy feedback.

[0008] As a preferred solution of the method for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station described in the present invention, the preprocessing includes installing temperature and humidity sensors in the underground powerhouse to form a distributed sensor network, wherein the sensor nodes are configured with unique identifiers, data tracking is performed, and filtering is performed on the collected data.

[0009] The filtering formula is:

[0010]

[0011] Among them, T filtered (t) is the data sequence after filtering, T(i) is the data sequence in the original unfiltered state, N is the size of the sliding window, t is the current time, and i is the variable index.

[0012] As a preferred solution of the method for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station described in the present invention, the data transmission to the central processor includes encrypting the preprocessed data and sending the encrypted data to the central processor via wireless transmission technology. After the central processor receives the data packet, it decrypts the data using a key and performs time series analysis and outlier detection on the decrypted data.

[0013] The outlier detection formula is:

[0014]

[0015] in, is the average value of the data, σ is the standard deviation, s is the threshold coefficient, and P(t) is the current detection data value.

[0016] As a preferred solution of the method for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station described in the present invention, the establishment of a multi-parameter correlation model includes integrating the preprocessed temperature and humidity data sets, equipment operation data sets, and personnel activity data sets into a unified data analysis platform, and performing synchronous analysis, extracting key features from each data set, establishing a correlation model using a machine learning algorithm, training the model using historical data, determining model parameters through an optimization algorithm and gradient descent update rules, and evaluating the accuracy and generalization ability of the model through cross-validation technology.

[0017] The extracted key features include the average value, variance and trend of temperature and humidity data, the working status, energy consumption and failure rate of equipment operation data, and the number of personnel, activity intensity and activity time period of personnel activity data.

[0018] The optimization algorithm formula is:

[0019]

[0020] Among them, L ( w ) is the loss function of a single sample, y (i) is the true label of the i-th sample, y' (i) is the predicted value, w is the parameter vector of the model, m is the total number of samples, and i is the variable index.

[0021] The gradient descent update rule formula is:

[0022]

[0023] Where η is the learning rate, is the gradient of the loss function with respect to the parameter w, w' is the updated model parameter vector, and w is the parameter vector of the model.

[0024] As a preferred solution of the method for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station described in the present invention, the association analysis includes using a trained model to perform association analysis on real-time data, predicting the environmental comfort index, analyzing the interaction between variables, identifying key influencing factors, and formulating automatic control strategies based on the results of the association analysis. The control strategies are converted into specific equipment control commands, and the working status of the ventilation and dehumidification equipment is automatically adjusted through the control system. The control effect is monitored in real time, and the model parameters and strategies are adjusted according to feedback, new data is collected regularly, and the model is retrained and optimized.

[0025] The execution of control instructions includes automatically adjusting the working status of ventilation and dehumidification equipment through the control system, monitoring the control effect in real time, and adjusting model parameters and strategies based on feedback.

[0026] As a preferred solution of the method for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station described in the present invention, the implementation of predictive maintenance and fault diagnosis includes real-time monitoring of environmental parameters, equipment operating parameters and equipment status indicators, transmitting the collected data to a central monitoring system through a sensor network, training a fault diagnosis model using historical data and equipment fault records, applying the model to process real-time data, predicting potential maintenance needs and faults, and when the model predicts a potential fault, the system will issue a maintenance warning and maintain and repair the equipment.

[0027] The fault diagnosis model formula is:

[0028] F ( t 2) =g ( X ( t 2) ,θ)

[0029] Among them, F(t2) is the fault prediction result at time t2, g is the fault diagnosis model function, X(t2) is the feature vector at time t2, and θ is the model parameter.

[0030] As a preferred solution of the method for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse in a hydropower station described in the present invention, the disaster warning and emergency response mechanism includes triggering the emergency response mechanism when the temperature is higher than 20°C and the humidity is greater than 50% RH, increasing ventilation and reducing dehumidification intensity, and notifying personnel in the underground powerhouse to evacuate through an alarm system. When the main power supply fails, the system automatically switches to the backup power supply. The system monitors the regulation effect in real time and adjusts the control strategy based on feedback.

[0031] The energy feedback includes evaluating the energy generated by the equipment during operation, determining the recoverable energy portion, and converting the mechanical energy or electrical energy generated by the equipment into a form of electrical energy that can be fed back to the power grid through an energy recovery device, regulating the electrical energy through a frequency converter and an energy feedback unit, feeding the regulated electrical energy back to the power grid, and then reusing the fed-back electrical energy.

[0032] Another object of the present invention is to provide a system for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse in a hydropower station. The present invention provides an efficient, safe, and intelligent environmental monitoring and control solution for an underground powerhouse in a hydropower station by integrating innovative technical means. By analyzing equipment operation data, the system of the present invention can predict potential failures and perform maintenance in advance, thereby reducing downtime and maintenance costs caused by sudden failures. When abnormal environmental parameters are detected, the system can quickly trigger an early warning and start an emergency response procedure to ensure the safety of personnel and equipment, and feed the remaining energy generated during the operation of the environmental control equipment back to the power grid, thereby improving energy utilization, reducing energy waste, and reducing operating costs.

[0033] As a preferred solution of the system for monitoring and analyzing the environmental temperature and humidity of the underground powerhouse of a hydropower station described in the present invention, it is characterized by including a data acquisition and preprocessing module, a data encryption and transmission module, a multi-parameter correlation model building module, a predictive maintenance and fault diagnosis module, and a disaster warning and emergency response module.

[0034] The data acquisition and preprocessing module is used to collect temperature and humidity data in the factory. The sensor node is configured with a unique identifier to track the data to ensure the traceability of the data. The collected data is filtered to reduce the impact of noise and outliers and improve the data quality.

[0035] The data encryption and transmission module is used to encrypt the preprocessed data to protect the security of the data during transmission, and send the encrypted data to the central processing unit through wireless transmission technology. After the central processing unit receives the data packet, it uses the key to decrypt the data, and performs time series analysis and outlier detection on the decrypted data to ensure the integrity and accuracy of the data.

[0036] The multi-parameter association model building module is used to integrate the pre-processed temperature and humidity data sets, equipment operation data sets and personnel activity data sets into a unified data analysis platform, extract key features from each data set, use machine learning algorithms to build association models, train the models through historical data, use optimization algorithms and gradient descent update rules to determine model parameters, and evaluate the accuracy and generalization ability of the models through cross-validation technology.

[0037] The predictive maintenance and fault diagnosis module is used to monitor environmental parameters, equipment operating parameters and equipment status indicators in real time, use historical data and equipment fault records to train fault diagnosis models, apply the models to process real-time data, and predict potential maintenance needs and faults. When the model predicts potential faults, the system will issue a maintenance warning and perform maintenance and repairs in a timely manner.

[0038] The predictive maintenance and fault diagnosis module is used to trigger an emergency response mechanism when the monitored environmental parameters exceed a preset safety range.

[0039] A computer device comprises 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 a method for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station are implemented.

[0040] 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 monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station are implemented.

[0041] Beneficial effects of the present invention: The present invention collects and pre-processes the temperature and humidity data in the underground powerhouse, and utilizes wireless transmission technology and encrypted communication protocols to ensure efficient and secure transmission of data, thereby improving the quality and security of the data; by establishing a multi-parameter correlation model, we have achieved a deep fusion analysis of environmental parameters, equipment operation, and personnel activities, and intelligently controlled ventilation and dehumidification equipment, thereby improving the intelligence and precision of environmental control; the introduction of predictive maintenance and fault diagnosis modules effectively predicts potential maintenance needs and faults, reduces the risk of equipment failure, and ensures the reliability of equipment operation. The establishment of a disaster warning and emergency response mechanism ensures that emergency measures can be taken quickly to protect the safety of personnel and equipment when the environment is abnormal; in addition, the energy feedback system improves energy utilization efficiency and reduces energy waste. Overall, the present invention forms an efficient, safe, and intelligent environmental monitoring and control system, which provides comprehensive protection for the underground powerhouse of a hydropower station and realizes the modernization and convenience of environmental management. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] 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:

[0043] Figure 1 An overall flow chart of a method for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station provided by an embodiment of the present invention.

[0044] Figure 2 An equipment deployment diagram of a method for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station provided by an embodiment of the present invention.

[0045] Figure 3 A system solution flow chart of a system for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station provided by 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 and Figure 2 , which is the first embodiment of the present invention, provides a method for monitoring and analyzing the temperature and humidity of an underground powerhouse environment of a hydropower station, comprising:

[0053] S1: Collect temperature and humidity data in the underground plant in real time, perform pre-processing, and transmit the data to the central processor through wireless transmission technology and encrypted communication protocol.

[0054] like Figure 2, temperature and humidity sensors are installed in the underground factory. The sensors form a distributed network to comprehensively monitor the environmental conditions in the factory. Each sensor node is assigned a unique identifier, which is used to track and manage the data source to ensure the traceability and accuracy of the data. The installed sensors will monitor and record the ambient temperature and humidity data in the factory in real time.

[0055] In order to improve data quality and reduce noise caused by environmental interference or sensor errors, sensor nodes will filter the collected raw data.

[0056] The filtering formula is:

[0057]

[0058] Among them, T filtered (t) is the data sequence after filtering, T(i) is the data sequence in the original unfiltered state, N is the size of the sliding window, t is the current time, and i is the variable index.

[0059] It should be noted that in order to ensure the security of data during transmission, the pre-processed data is encrypted using the Advanced Encryption Standard, and the encrypted data is sent to the central processing unit through wireless transmission technology, such as LoRa. After the central processing unit receives the data packet, it uses the corresponding decryption key to decrypt the data. At the central processing unit end, the decrypted data is further processed, including time series analysis and outlier detection.

[0060] The encryption formula is:

[0061] C=E k( P)

[0062] Among them, C is the encrypted data, P is the preprocessed data, k is the key, and E is the encryption function.

[0063] The data transmission is represented as:

[0064] T transmitted (t1) = {C, t1, SensorID}

[0065] Among them, T transmitted (t) is the transmitted data packet, C is the encrypted data, t1 is the timestamp of data acquisition, and SensorID is the unique identifier of the sensor node that sends the data.

[0066] The decryption formula is:

[0067] P=D k( C)

[0068] Among them, P is the decrypted data, that is, the pre-processed data, D is the decryption function, and k is the key.

[0069] The outlier detection formula is:

[0070]

[0071] in, is the average value of the data, σ is the standard deviation, s is the threshold coefficient, and P(t) is the current detection data value.

[0072] S2: Establish a multi-parameter correlation model to correlate the pre-processed temperature and humidity data with the equipment operation data and personnel activity data. According to the correlation analysis results, automatically adjust the ventilation and dehumidification equipment to intelligently control the temperature and humidity of the environment.

[0073] Furthermore, the establishment of the multi-parameter association model includes integrating the preprocessed temperature and humidity data sets, equipment operation data sets, and personnel activity data sets into a unified data analysis platform, and performing synchronous analysis, extracting key features from each data set, using a machine learning algorithm to establish an association model, using historical data to train the model, determining model parameters through an optimization algorithm and gradient descent update rules, and evaluating the accuracy and generalization ability of the model through cross-validation technology.

[0074] The extracted key features include the average value, variance and trend of temperature and humidity data, the working status, energy consumption and failure rate of equipment operation data, and the number of personnel, activity intensity and activity time period of personnel activity data.

[0075] It should be noted that the setting model formula is:

[0076] Y(t)=β0+β1*T filtered (t)+β2*D(t)+β3*A(t)+ε

[0077] Among them, T filtered (t) is the transmitted temperature and humidity data packet, β0 is the intercept term, β1, β2 and β3 are the independent variable coefficients, Y(t) is the environmental temperature and humidity control target variable, D(t) is the equipment operation data, A(t) is the personnel activity data, and ε is the error term.

[0078] The optimization algorithm formula is:

[0079]

[0080] Among them, L ( w ) is the loss function of a single sample, y (i) is the true label of the i-th sample, y' (i)is the predicted value, w is the parameter vector of the model, m is the total number of samples, and i is the variable index.

[0081] It should be noted that the gradient descent update rule formula is:

[0082]

[0083] Where η is the learning rate, is the gradient of the loss function with respect to the parameter w, w' is the updated model parameter vector, and w is the parameter vector of the model.

[0084] The cross-validation includes evenly dividing the entire dataset into S subsets of equal size, which are called "folds". For each fold, one fold is used as a validation set, and the remaining S-1 folds are combined as a training set to train the model. After the model training is completed, the current validation set is used to evaluate the performance of the model. The training and validation process is repeated until each fold is used as a validation set once in turn. By calculating the average performance of all S validations, a comprehensive indicator is obtained, which is regarded as the final performance indicator of the model, thereby having a comprehensive evaluation of the generalization ability of the model.

[0085] The association analysis includes using the trained model to perform association analysis on real-time data, predicting the environmental comfort index, analyzing the interaction between variables, identifying key influencing factors, formulating automatic control strategies based on the association analysis results, converting the control strategies into specific equipment control commands, automatically adjusting the working status of ventilation and dehumidification equipment through the control system, monitoring the control effect in real time, adjusting model parameters and strategies based on feedback, regularly collecting new data, retraining and optimizing the model, and improving the accuracy and efficiency of the control system.

[0086] Furthermore, the automatic control strategy includes setting the lower threshold of comfort level to -6 and the upper threshold to 6. If the comfort level is less than -6, ventilation and dehumidification need to be increased; if the comfort level is greater than 6, ventilation and humidification need to be reduced.

[0087] The execution of control instructions includes automatically adjusting the working status of ventilation and dehumidification equipment through the control system, monitoring the control effect in real time, and adjusting model parameters and strategies based on feedback.

[0088] S3: Implement predictive maintenance and fault diagnosis based on real-time data and equipment operating status. When environmental anomalies are detected, activate the disaster warning and emergency response mechanism, and recover the excess energy generated during the operation of environmental control equipment to the power grid through energy feedback.

[0089] Furthermore, the implementation of predictive maintenance and fault diagnosis includes real-time monitoring of environmental parameters, equipment operating parameters and equipment status indicators, transmitting the collected data to a central monitoring system through a sensor network, training a fault diagnosis model using historical data and equipment fault records, applying the model to process real-time data, and predicting potential maintenance needs and faults. When the model predicts a potential fault, the system will issue a maintenance warning and maintain and repair the equipment.

[0090] The fault diagnosis model formula is:

[0091] F(t2)=g(X(t2),θ )

[0092] Among them, F(t2) is the fault prediction result at time t2, g is the fault diagnosis model function, X(t2) is the feature vector at time t2, and θ is the model parameter.

[0093] Furthermore, the disaster warning and emergency response mechanism includes triggering the emergency response mechanism when the temperature is higher than 20°C and the humidity is greater than 50% RH, increasing ventilation and reducing dehumidification intensity, notifying personnel in the underground factory to evacuate through the alarm system, and when the main power supply fails, the system automatically switches to the backup power supply. The system monitors the regulation effect in real time and adjusts the control strategy based on feedback.

[0094] The energy feedback includes evaluating the energy generated by the equipment during operation, determining the recoverable energy portion, and converting the mechanical energy or electrical energy generated by the equipment into a form of electrical energy that can be fed back to the power grid through an energy recovery device, regulating the electrical energy through a frequency converter and an energy feedback unit, feeding the regulated electrical energy back to the power grid, and then reusing the fed-back electrical energy.

[0095] 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.

[0096] Example 2, reference Figure 3 , which is the second embodiment of the present invention, provides a system for monitoring and analyzing the temperature and humidity of the underground powerhouse environment of a hydropower station, including a data acquisition and preprocessing module 100, a data encryption and transmission module 200, a multi-parameter correlation model building module 300, a predictive maintenance and fault diagnosis module 400, and a disaster warning and emergency response module 500.

[0097] The data acquisition and preprocessing module 100 is used to collect temperature and humidity data in the factory. The sensor node is configured with a unique identifier to track the data to ensure the traceability of the data. The collected data is filtered to reduce the impact of noise and outliers and improve the data quality.

[0098] The data encryption and transmission module 200 is used to encrypt the preprocessed data to protect the security of the data during transmission, and send the encrypted data to the central processing unit through wireless transmission technology. After the central processing unit receives the data packet, it uses the key to decrypt the data, and performs time series analysis and outlier detection on the decrypted data to ensure the integrity and accuracy of the data.

[0099] The multi-parameter association model building module 300 is used to integrate the pre-processed temperature and humidity data sets, equipment operation data sets and personnel activity data sets into a unified data analysis platform, extract key features from each data set, use machine learning algorithms to build association models, train the model through historical data, use optimization algorithms and gradient descent update rules to determine model parameters, and evaluate the accuracy and generalization ability of the model through cross-validation technology.

[0100] The predictive maintenance and fault diagnosis module 400 is used to monitor environmental parameters, equipment operating parameters and equipment status indicators in real time, use historical data and equipment fault records to train fault diagnosis models, apply the models to process real-time data, and predict potential maintenance needs and faults. When the model predicts potential faults, the system will issue a maintenance warning and perform maintenance and repairs in a timely manner.

[0101] The predictive maintenance and fault diagnosis module 500 is used to trigger an emergency response mechanism when the monitored environmental parameters exceed a preset safety range.

[0102] 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.

[0103] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that:

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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 monitoring and analyzing the temperature and humidity of an underground powerhouse in a hydropower station, characterized in that: include, Collect temperature and humidity data in the underground plant in real time, pre-process it, and transmit the data to the central processor through wireless transmission technology and encrypted communication protocol; Establish a multi-parameter correlation model to correlate the pre-processed temperature and humidity data with the equipment operation data and personnel activity data. According to the correlation analysis results, automatically adjust the ventilation and dehumidification equipment to intelligently control the temperature and humidity of the environment. Predictive maintenance and fault diagnosis are implemented based on real-time data and equipment operating status. When environmental abnormalities are detected, disaster warning and emergency response mechanisms are activated, and the excess energy generated during the operation of environmental control equipment is recovered to the power grid through energy feedback.

2. A method for monitoring and analyzing the temperature and humidity of an underground powerhouse environment of a hydropower station as claimed in claim 1, characterized in that: The preprocessing includes installing temperature and humidity sensors in the underground plant to form a distributed sensor network, configuring the sensor nodes with unique identifiers, tracking data, and filtering the collected data; The filtering formula is: Among them, T filtered (t) is the data sequence after filtering, T(i) is the data sequence in the original unfiltered state, N is the size of the sliding window, t is the current time, and i is the variable index.

3. A method for monitoring and analyzing the temperature and humidity of an underground powerhouse environment of a hydropower station as claimed in claim 2, characterized in that: The transmitting of data to the central processor includes encrypting the pre-processed data and sending the encrypted data to the central processor via wireless transmission technology. After receiving the data packet, the central processor decrypts the data using a key and performs time series analysis and outlier detection on the decrypted data. The outlier detection formula is: in, is the average value of the data, σ is the standard deviation, s is the threshold coefficient, and P(t) is the current detection data value.

4. A method for monitoring and analyzing the temperature and humidity of an underground powerhouse environment of a hydropower station as claimed in claim 3, characterized in that: The establishment of the multi-parameter association model includes integrating the pre-processed temperature and humidity data set, the equipment operation data set and the personnel activity data set into a unified data analysis platform, and performing synchronous analysis, extracting key features from each data set, establishing the association model using a machine learning algorithm, training the model using historical data, determining the model parameters through an optimization algorithm and a gradient descent update rule, and evaluating the accuracy and generalization ability of the model through a cross-validation technique; The extracted key features include the average value, variance and trend of temperature and humidity data, the working status, energy consumption and failure rate of equipment operation data, and the number of personnel, activity intensity and activity time period of personnel activity data; The optimization algorithm formula is: Among them, L ( w ) is the loss function of a single sample, y (i) is the true label of the i-th sample, y' (i) is the predicted value, w is the parameter vector of the model, m is the total number of samples, and i is the variable index; The gradient descent update rule formula is: Where η is the learning rate, is the gradient of the loss function with respect to the parameter w, w' is the updated model parameter vector, and w is the parameter vector of the model.

5. A method for monitoring and analyzing the temperature and humidity of an underground powerhouse environment of a hydropower station as claimed in claim 4, characterized in that: The association analysis includes using the trained model to perform association analysis on real-time data, predicting the environmental comfort index, analyzing the interaction between variables, identifying key influencing factors, formulating automatic control strategies based on the association analysis results, converting the control strategies into specific equipment control commands, automatically adjusting the working status of ventilation and dehumidification equipment through the control system, monitoring the control effect in real time, and adjusting model parameters and strategies based on feedback, regularly collecting new data, and retraining and optimizing the model; The execution of control instructions includes automatically adjusting the working status of ventilation and dehumidification equipment through the control system, monitoring the control effect in real time, and adjusting model parameters and strategies based on feedback.

6. A method for monitoring and analyzing the temperature and humidity of an underground powerhouse environment of a hydropower station as claimed in claim 5, characterized in that: The implementation of predictive maintenance and fault diagnosis includes real-time monitoring of environmental parameters, equipment operating parameters and equipment status indicators, transmitting the collected data to a central monitoring system through a sensor network, using historical data and equipment fault records to train a fault diagnosis model, applying the model to process real-time data, predicting potential maintenance needs and faults, and when the model predicts a potential fault, the system will issue a maintenance warning and perform maintenance and repair on the equipment; The fault diagnosis model formula is: F(t2)=g(X(t2),θ ) Among them, F(t2) is the fault prediction result at time t2, g is the fault diagnosis model function, X(t2) is the feature vector at time t2, and θ is the model parameter.

7. A method for monitoring and analyzing the temperature and humidity of an underground powerhouse environment of a hydropower station as claimed in claim 6, characterized in that: The disaster warning and emergency response mechanism includes triggering the emergency response mechanism when the temperature is higher than 20°C and the humidity is greater than 50%RH, increasing ventilation and reducing dehumidification, notifying the personnel in the underground plant to evacuate through the alarm system, and automatically switching to the backup power supply when the main power supply fails. The system monitors the control effect in real time and adjusts the control strategy according to feedback; The energy feedback includes evaluating the energy generated by the equipment during operation, determining the recoverable energy portion, and converting the mechanical energy or electrical energy generated by the equipment into a form of electrical energy that can be fed back to the power grid through an energy recovery device, regulating the electrical energy through a frequency converter and an energy feedback unit, feeding the regulated electrical energy back to the power grid, and then reusing the fed-back electrical energy.

8. A system using the method for monitoring and analyzing the temperature and humidity of an underground powerhouse environment of a hydropower station as claimed in any one of claims 1 to 7, characterized in that: It includes data acquisition and preprocessing module, data encryption and transmission module, multi-parameter correlation model building module, predictive maintenance and fault diagnosis module, and disaster warning and emergency response module; The data acquisition and preprocessing module is used to collect temperature and humidity data in the factory. The sensor node is configured with a unique identifier to track the data to ensure the traceability of the data. The collected data is filtered to reduce the impact of noise and outliers and improve the data quality. The data encryption and transmission module is used to encrypt the preprocessed data to protect the security of the data during transmission, and send the encrypted data to the central processing unit through wireless transmission technology. After the central processing unit receives the data packet, it uses the key to decrypt the data, and performs time series analysis and outlier detection on the decrypted data to ensure the integrity and accuracy of the data; The multi-parameter association model building module is used to integrate the pre-processed temperature and humidity data sets, equipment operation data sets, and personnel activity data sets into a unified data analysis platform, extract key features from each data set, use machine learning algorithms to build association models, train the models with historical data, use optimization algorithms and gradient descent update rules to determine model parameters, and evaluate the accuracy and generalization ability of the models through cross-validation technology; The predictive maintenance and fault diagnosis module is used to monitor environmental parameters, equipment operating parameters and equipment status indicators in real time, use historical data and equipment fault records to train fault diagnosis models, apply the models to process real-time data, and predict potential maintenance needs and faults. When the model predicts a potential fault, the system will issue a maintenance warning and perform maintenance and repair in a timely manner; The predictive maintenance and fault diagnosis module is used to trigger an emergency response mechanism when the monitored environmental parameters exceed a preset safety range.

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 a method for monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station as 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 monitoring and analyzing the environmental temperature and humidity of an underground powerhouse of a hydropower station as described in any one of claims 1 to 7 are implemented.

Images