Multi-channel data management system and management method for heat supply network equipment

Abstract

The invention discloses a multi-channel data management system and management method for heat supply network equipment, and relates to the field of management for heat supply network equipment, and the system comprises a data acquisition unit, a data transmission unit, a data storage unit, a data analysis unit and a data application unit. According to the multi-channel data management system and management method for the heat supply network equipment, the system has remarkable advantages in the heat supply network industry, the operation management level of the heat supply network equipment is greatly improved, the operation and maintenance cost and the energy loss are reduced, the reliability and the stability of a heat supply network system are enhanced, a model can be continuously optimized, and the management efficiency is improved. The system adapts to the dynamic change of heat supply network operation, can effectively realize the intelligentization of heat supply network management, can effectively reduce the energy consumption, can prolong the service life of heat supply network equipment, can comprehensively and deeply understand the operation condition of the heat supply network equipment, can excavate potential optimization space and fault hidden dangers, and provides powerful support for the fine management of the heat supply network.

Description

Technical Field

[0001] The present invention relates to the field of management of heating network equipment, and in particular to a multi-channel data management system and a management method for heating network equipment. Background Art

[0002] Heating network equipment is a general term for a series of devices used to transport thermal energy in a centralized heating system, mainly including heat source equipment, heat exchange equipment, heating network circulation equipment, heating network pipelines and accessories.

[0003] The existing management system for heating network equipment cannot deeply analyze the operating rules of heating network equipment under different conditions, resulting in the inability to support the subsequent optimization and operation and maintenance management of the heating network equipment. At the same time, the accuracy of fault diagnosis cannot be guaranteed.

[0004] Therefore, it is necessary to propose a multi-channel data management system and management method for heating network equipment to solve the above problems. Summary of the invention

[0005] The main purpose of the present invention is to provide a multi-channel data management system and management method for heating network equipment, which can effectively solve the problems in the background technology.

[0006] To achieve the above object, the technical solution adopted by the present invention is:

[0007] A multi-channel data management system for heating network equipment, comprising a data acquisition unit, a data transmission unit, a data storage unit, a data analysis unit, and a data application unit, wherein the data acquisition unit collects heating network equipment data based on an intelligent sensor matrix and encrypted transmission;

[0008] The data transmission unit is used to construct an optical communication network based on space division multiplexing and wavelength division multiplexing technology to achieve ultra-high-speed data transmission;

[0009] The method is used to store heating network data and reheat network data;

[0010] The data analysis unit is used to organically integrate the structured data and unstructured data of the heating network equipment, and through cross-modal feature extraction and correlation analysis, comprehensively and deeply understand the operating status of the heating network equipment, and explore potential optimization space and potential fault hazards;

[0011] The data application unit is based on an intelligent decision-making system of reinforcement learning, which automatically generates the optimal heating network scheduling strategy, equipment maintenance plan and energy allocation plan according to the data analysis results.

[0012] Preferably, the data acquisition unit includes an intelligent sensor matrix arrangement module and an encrypted transmission module, wherein the intelligent sensor matrix arrangement module includes a sensor deployment and initialization module, which is used to install MEMS sensors and flow sensors, temperature sensors, humidity sensors, and pressure sensors at the locations of the heat network equipment structure according to the structure of the heat network equipment and the distribution of key monitoring points; initialize and set each sensor, including calibrating its measurement range and accuracy parameters, and assigning a unique identification code and network address to it for identification and positioning in the data acquisition network;

[0013] The multi-channel data synchronous acquisition startup module is used to send synchronous acquisition instructions to all sensors in the intelligent sensor matrix through the central controller after the system is started. The MEMS sensor starts to collect pressure, flow, and data channel information with fast dynamic changes at a frequency of 100 times per second. The flow sensor, temperature sensor, humidity sensor, and pressure sensor collect flow, temperature, humidity, and pressure data at a frequency of 10 times per second. The sensor converts the collected original analog signal into a digital signal and caches it locally for 1 second, waiting for data transmission instructions;

[0014] In the data quality preliminary verification module, each sensor uses the built-in microprocessor to perform preliminary quality verification on the collected data. When data quality problems are found, the sensor automatically calibrates and re-collects data.

[0015] Preferably, the encryption transmission module includes a key generation and distribution module, and a key generation device is deployed in the central node of the data management system and each sensor node, and a pair of mutually related keys is generated between the central node and the sensor node;

[0016] Data encryption and transmission request module, the sensor node uses the generated key to encrypt the data after preliminary processing, and uses the symmetric encryption algorithm to encrypt the data into ciphertext. The sensor node sends a data transmission request to the data aggregation node, and the request contains the encrypted data length and data type;

[0017] Data transmission and reception verification module, after the data aggregation node receives the transmission request, it establishes a secure communication channel with the sensor node. The sensor node sends the encrypted data to the data aggregation node via wireless transmission. After the data aggregation node receives the data, it first uses the key to decrypt the data and verifies the integrity of the decrypted data. When the data verification passes, the data aggregation node will further process the data; when the data verification fails, the data aggregation node will send a retransmission request to the sensor node, requesting the data to be resent.

[0018] Preferably, the data storage unit comprises a data storage module and an error correction coding module, wherein the data storage module is used to store data and reproduce data.

[0019] Preferably, the error correction coding module includes a coding module, an error detection module and an error correction module, wherein the coding module selects Shor code for error correction coding scheme;

[0020] The error detection module is used to detect information errors caused during information transmission and storage. It obtains information about the error by measuring the data. Based on the results obtained, it extracts the error signs to determine whether an error has occurred and where the error may occur.

[0021] The error correction module is used to determine the type and location of the error based on the extracted error symptoms.

[0022] Preferably, the data analysis unit includes a coding module, a model training module, a model evaluation and optimization module, and a result analysis module, wherein the coding module selects a suitable coding method for coding processing according to the characteristics of the data;

[0023] The model training module is used to build a deep learning model according to specific analysis tasks, conduct multiple iterative training, and continuously adjust the model parameters to minimize the loss function and optimize the objective function, so that the model can accurately analyze and predict the heating network equipment data.

[0024] Preferably, the model evaluation and optimization module selects appropriate evaluation indicators based on the nature of the analysis task, including accuracy, recall, mean square error, and F1 value, performs performance evaluation on the trained model, uses a test data set to evaluate the model, and calculates corresponding evaluation indicator values ​​to understand the generalization ability and prediction accuracy of the model on unseen data. When the model performance does not meet expectations, an optimization algorithm is used to further optimize and adjust the model parameters.

[0025] Preferably, the result analysis module is used to interpret and understand the results obtained from the computationally assisted deep analysis, analyze the patterns, trends and potential problems contained in the heating network equipment data, apply the analysis results to the operation optimization, fault diagnosis and energy consumption management of the heating network equipment, formulate corresponding strategies and measures, and continuously adjust and optimize the data preprocessing methods, encoding methods, model structures and parameters based on feedback from actual applications.

[0026] Preferably, the data application unit includes a virtual reality operation and maintenance platform, which is used to view the operating status, data indicators and fault locations of the heating network equipment through the digital twin system to achieve remote collaboration and precise operation guidance.

[0027] A multi-channel data management method for heating network equipment, using a multi-channel data management system for heating network equipment, includes the following steps:

[0028] S1: According to the structure of the heating network equipment and the distribution of key monitoring points, MEMS sensors and flow sensors, temperature sensors, humidity sensors, and pressure sensors are installed at the parts of the heating network equipment structure, and the measurement range and accuracy parameters of the sensors are calibrated. Unique identification codes and network addresses are assigned to them. High-precision temperature and pressure flow sensors, temperature sensors, humidity sensors, and pressure sensors are installed at the inlet and outlet of the heating network pipeline to monitor the inlet and outlet status of the heat medium. At the same time, MEMS sensors are evenly distributed along the pipeline to capture dynamic changes in the heat medium transmission process. The sensors automatically verify the data they transmit and receive the qualified data.

[0029] S2: store data information;

[0030] S3: Use Shor code for error correction coding to detect information errors caused during information transmission and storage, extract error signs, determine whether an error has occurred and where the error may have occurred, and correct the error according to its type and location;

[0031] S4: Analyze and predict the heating network equipment data based on the deep learning model, interpret and understand the results, analyze the patterns, trends and potential problems contained in the heating network equipment data, apply the analysis results to the operation optimization, fault diagnosis and energy consumption management of the heating network equipment, and formulate corresponding strategies and measures.

[0032] Compared with the prior art, the present invention provides a multi-channel data management system and management method for heating network equipment, which has the following beneficial effects:

[0033] The multi-channel data management system and management method for the heating network equipment have significant advantages in the heating network industry. It greatly improves the operation and management level of the heating network equipment, reduces the operation and maintenance costs and energy loss, and enhances the reliability and stability of the heating network system. It can continuously optimize the model and adapt to the dynamic changes in the operation of the heating network. It can effectively realize the intelligent management of the heating network, effectively reduce energy consumption, and extend the service life of the heating network equipment. It can fully and deeply understand the operation status of the heating network equipment, explore potential optimization space and hidden faults, and provide strong support for the refined management of the heating network. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a system block diagram of the present invention;

[0035] Figure 2 is a system block diagram of a data acquisition unit of the present invention;

[0036] Figure 3 is a system block diagram of a data storage unit of the present invention;

[0037] Figure 4 It is a system block diagram of the data analysis unit of the present invention. DETAILED DESCRIPTION

[0038] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0039] Embodiment 1:

[0040] like Figure 1-Figure 4 As shown, a multi-channel data management system for heating network equipment, a multi-channel data management system for heating network equipment, including a data acquisition unit, a data transmission unit, a data storage unit, a data analysis unit, and a data application unit. The data acquisition unit collects heating network equipment data based on an intelligent sensor matrix and encrypted transmission;

[0041] The data transmission unit is used to build an optical communication network based on space division multiplexing and wavelength division multiplexing technology to achieve ultra-high-speed data transmission;

[0042] Used to store heating network data and reheating network data;

[0043] The data analysis unit is used to organically integrate the structured data and unstructured data of the heating network equipment, and through cross-modal feature extraction and correlation analysis, comprehensively and deeply understand the operating status of the heating network equipment, and explore potential optimization space and potential fault hazards;

[0044] The data application unit is based on an intelligent decision-making system based on reinforcement learning, which automatically generates the optimal heating network scheduling strategy, equipment maintenance plan and energy allocation plan according to the data analysis results.

[0045] The data acquisition unit includes an intelligent sensor matrix layout module and an encrypted transmission module, wherein the intelligent sensor matrix layout module includes a sensor deployment and initialization module, which is used to install MEMS sensors and flow sensors, temperature sensors, humidity sensors, and pressure sensors at the locations of the heat network equipment structure according to the structure of the heat network equipment and the distribution of key monitoring points; initialize and set each sensor, including calibrating its measurement range and accuracy parameters, and assigning a unique identification code and network address to it for identification and positioning in the data acquisition network;

[0046] The multi-channel data synchronous acquisition startup module is used to send synchronous acquisition instructions to all sensors in the intelligent sensor matrix through the central controller after the system is started. The MEMS sensor starts to collect pressure, flow, and data channel information with fast dynamic changes at a frequency of 100 times per second. The flow sensor, temperature sensor, humidity sensor, and pressure sensor collect flow, temperature, humidity, and pressure data at a frequency of 10 times per second. The sensor converts the collected original analog signal into a digital signal and caches it locally for 1 second, waiting for data transmission instructions;

[0047] In the data quality preliminary verification module, each sensor uses the built-in microprocessor to perform preliminary quality verification on the collected data. When data quality problems are found, the sensor automatically calibrates and re-collects data.

[0048] The encryption transmission module includes a key generation and distribution module, which deploys key generation devices in the central node of the data management system and each sensor node, and generates a pair of mutually related keys between the central node and the sensor node;

[0049] Data encryption and transmission request module, the sensor node uses the generated key to encrypt the data after preliminary processing, and uses the symmetric encryption algorithm to encrypt the data into ciphertext. The sensor node sends a data transmission request to the data aggregation node, and the request contains the encrypted data length and data type;

[0050] Data transmission and reception verification module, after the data aggregation node receives the transmission request, it establishes a secure communication channel with the sensor node. The sensor node sends the encrypted data to the data aggregation node via wireless transmission. After the data aggregation node receives the data, it first uses the key to decrypt the data and verifies the integrity of the decrypted data. When the data verification passes, the data aggregation node will further process the data; when the data verification fails, the data aggregation node will send a retransmission request to the sensor node, requesting the data to be resent.

[0051] The data storage unit comprises a data storage module and an error correction coding module, wherein the data storage module is used to store data and reproduce data.

[0052] The error correction coding module includes a coding module, an error detection module and an error correction module, wherein the coding module selects Shor code for error correction coding scheme;

[0053] The error detection module is used to detect information errors caused during information transmission and storage. It obtains information about the error by measuring the data. Based on the results obtained, it extracts the error signs to determine whether an error has occurred and where the error may occur.

[0054] The error correction module is used to determine the type and location of the error based on the extracted error symptoms.

[0055] The data analysis unit includes a coding module, a model training module, a model evaluation and optimization module, and a result analysis module. The coding module selects a suitable coding method for coding processing according to the characteristics of the data;

[0056] The model training module is used to build a deep learning model according to specific analysis tasks, conduct multiple iterative training, and continuously adjust the model parameters to minimize the loss function and optimize the objective function, so that the model can accurately analyze and predict the data of the heating network equipment;

[0057] The model evaluation and optimization module selects appropriate evaluation indicators based on the nature of the analysis task, including accuracy, recall, mean square error, and F1 value, and evaluates the performance of the trained model. It uses the test data set to evaluate the model and calculates the corresponding evaluation indicator values ​​to understand the generalization ability and prediction accuracy of the model on unseen data. When the model performance does not meet expectations, the optimization algorithm is used to further optimize the model parameters.

[0058] The result analysis module is used to interpret and understand the results obtained from the computationally assisted deep analysis, analyze the patterns, trends and potential problems contained in the heating network equipment data, apply the analysis results to the operation optimization, fault diagnosis and energy consumption management of the heating network equipment, formulate corresponding strategies and measures, and continuously adjust and optimize the data preprocessing methods, encoding methods, model structures and parameters based on feedback from actual applications.

[0059] The data application unit includes a virtual reality operation and maintenance platform, which is used to view the operating status, data indicators and fault locations of heating network equipment through the digital twin system, and realize remote collaboration and precise operation guidance.

[0060] Embodiment 2:

[0061] A multi-channel data management method for heating network equipment, using a multi-channel data management system for heating network equipment, includes the following steps:

[0062] S1: According to the structure of the heating network equipment and the distribution of key monitoring points, MEMS sensors and flow sensors, temperature sensors, humidity sensors, and pressure sensors are installed at the parts of the heating network equipment structure, and the measurement range and accuracy parameters of the sensors are calibrated. Unique identification codes and network addresses are assigned to them. High-precision temperature and pressure flow sensors, temperature sensors, humidity sensors, and pressure sensors are installed at the inlet and outlet of the heating network pipeline to monitor the inlet and outlet status of the heat medium. At the same time, MEMS sensors are evenly distributed along the pipeline to capture dynamic changes in the heat medium transmission process. The sensors automatically verify the data they transmit and receive the qualified data.

[0063] S2: store data information;

[0064] S3: Use Shor code for error correction coding to detect information errors caused during information transmission and storage, extract error signs, determine whether an error has occurred and where the error may have occurred, and correct the error according to its type and location;

[0065] S4: Analyze and predict the heating network equipment data based on the deep learning model, interpret and understand the results, analyze the patterns, trends and potential problems contained in the heating network equipment data, apply the analysis results to the operation optimization, fault diagnosis and energy consumption management of the heating network equipment, and formulate corresponding strategies and measures.

[0066] This system has significant advantages in the heating network industry. It greatly improves the operation and management level of heating network equipment, reduces operation and maintenance costs and energy losses, enhances the reliability and stability of the heating network system, can continuously optimize the model, adapt to the dynamic changes in the operation of the heating network, and effectively realize the intelligent management of the heating network. It can effectively reduce energy consumption and extend the service life of the heating network equipment. It can fully and deeply understand the operating status of the heating network equipment, explore potential optimization space and hidden faults, and provide strong support for the refined management of the heating network.

[0067] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A multi-channel data management system for heating network equipment, comprising a data acquisition unit, a data transmission unit, a data storage unit, a data analysis unit, and a data application unit, characterized in that: The data acquisition unit collects the data of the heating network equipment based on the intelligent sensor matrix and encrypted transmission; The data transmission unit is used to construct an optical communication network based on space division multiplexing and wavelength division multiplexing technology to achieve ultra-high-speed data transmission; The method is used to store heating network data and reheat network data; The data analysis unit is used to organically integrate the structured data and unstructured data of the heating network equipment, and through cross-modal feature extraction and correlation analysis, comprehensively and deeply understand the operating status of the heating network equipment, and explore potential optimization space and potential fault hazards; The data application unit is based on an intelligent decision-making system of reinforcement learning, which automatically generates the optimal heating network scheduling strategy, equipment maintenance plan and energy allocation plan according to the data analysis results.

2. A multi-channel data management system for heating network equipment according to claim 1, characterized in that: The data acquisition unit includes an intelligent sensor matrix arrangement module and an encrypted transmission module, wherein the intelligent sensor matrix arrangement module includes a sensor deployment and initialization module, which is used to install MEMS sensors and flow sensors, temperature sensors, humidity sensors, and pressure sensors at the locations of the heat network equipment structure according to the structure of the heat network equipment and the distribution of key monitoring points; initialize and set each sensor, including calibrating its measurement range and accuracy parameters, and assigning a unique identification code and network address to it for identification and positioning in the data acquisition network; The multi-channel data synchronous acquisition startup module is used to send synchronous acquisition instructions to all sensors in the intelligent sensor matrix through the central controller after the system is started. The MEMS sensor starts to collect pressure, flow, and data channel information with fast dynamic changes at a frequency of 100 times per second. The flow sensor, temperature sensor, humidity sensor, and pressure sensor collect flow, temperature, humidity, and pressure data at a frequency of 10 times per second. The sensor converts the collected original analog signal into a digital signal and caches it locally for 1 second, waiting for data transmission instructions; In the data quality preliminary verification module, each sensor uses the built-in microprocessor to perform preliminary quality verification on the collected data. When data quality problems are found, the sensor automatically calibrates and re-collects data.

3. A multi-channel data management system for heating network equipment according to claim 2, characterized in that: The encryption transmission module includes a key generation and distribution module, which deploys key generation devices at the central node and each sensor node of the data management system, and generates a pair of mutually related keys between the central node and the sensor node; Data encryption and transmission request module, the sensor node uses the generated key to encrypt the data after preliminary processing, and uses the symmetric encryption algorithm to encrypt the data into ciphertext. The sensor node sends a data transmission request to the data aggregation node, and the request contains the encrypted data length and data type; Data transmission and reception verification module, after the data aggregation node receives the transmission request, it establishes a secure communication channel with the sensor node. The sensor node sends the encrypted data to the data aggregation node via wireless transmission. After the data aggregation node receives the data, it first uses the key to decrypt the data and verifies the integrity of the decrypted data. When the data verification passes, the data aggregation node will further process the data; when the data verification fails, the data aggregation node will send a retransmission request to the sensor node, requesting the data to be resent.

4. A multi-channel data management system for heating network equipment according to claim 1, characterized in that: The data storage unit comprises a data storage module and an error correction coding module, wherein the data storage module is used for storing data and retrieving data.

5. A multi-channel data management system for heating network equipment according to claim 4, characterized in that: The error correction coding module includes a coding module, an error detection module and an error correction module, wherein the coding module selects Shor code for error correction coding scheme; The error detection module is used to detect information errors caused during information transmission and storage. It obtains information about the error by measuring the data. Based on the results obtained, it extracts the error signs to determine whether an error has occurred and where the error may occur. The error correction module is used to determine the type and location of the error based on the extracted error symptoms.

6. A multi-channel data management system for heating network equipment according to claim 1, characterized in that: The data analysis unit includes a coding module, a model training module, a model evaluation and optimization module, and a result analysis module, wherein the coding module selects a suitable coding method for coding processing according to the characteristics of the data; The model training module is used to build a deep learning model according to specific analysis tasks, conduct multiple iterative training, and continuously adjust the model parameters to minimize the loss function and optimize the objective function, so that the model can accurately analyze and predict the heating network equipment data.

7. A multi-channel data management system for heating network equipment according to claim 6, characterized in that: The model evaluation and optimization module selects appropriate evaluation indicators based on the nature of the analysis task, including accuracy, recall, mean square error, and F1 value, performs performance evaluation on the trained model, uses a test data set to evaluate the model, and calculates the corresponding evaluation indicator values ​​to understand the model's generalization ability and prediction accuracy on unseen data. When the model performance does not meet expectations, an optimization algorithm is used to further optimize the model parameters.

8. A multi-channel data management system for heating network equipment according to claim 6, characterized in that: The result analysis module is used to interpret and understand the results obtained from the computationally assisted deep analysis, analyze the laws, trends and potential problems contained in the heating network equipment data, apply the analysis results to the operation optimization, fault diagnosis and energy consumption management of the heating network equipment, formulate corresponding strategies and measures, and continuously adjust and optimize the data preprocessing methods, encoding methods, model structures and parameters based on feedback from actual applications.

9. A multi-channel data management system for heating network equipment according to claim 1, characterized in that: The data application unit includes a virtual reality operation and maintenance platform, which is used to view the operating status, data indicators and fault locations of heating network equipment through a digital twin system to achieve remote collaboration and precise operation guidance.

10. A multi-channel data management method for heating network equipment, using the multi-channel data management system for heating network equipment according to claim 1, characterized in that: The steps include: S1: According to the structure of the heating network equipment and the distribution of key monitoring points, MEMS sensors and flow sensors, temperature sensors, humidity sensors, and pressure sensors are installed at the parts of the heating network equipment structure, and the measurement range and accuracy parameters of the sensors are calibrated. Unique identification codes and network addresses are assigned to them. High-precision temperature and pressure flow sensors, temperature sensors, humidity sensors, and pressure sensors are installed at the inlet and outlet of the heating network pipeline to monitor the inlet and outlet status of the heat medium. At the same time, MEMS sensors are evenly distributed along the pipeline to capture dynamic changes in the heat medium transmission process. The sensors automatically verify the data they transmit and receive the qualified data. S2: store data information; S3: Use Shor code for error correction coding to detect information errors caused during information transmission and storage, extract error signs, determine whether an error has occurred and where the error may have occurred, and correct the error according to its type and location; S4: Analyze and predict the heating network equipment data based on the deep learning model, interpret and understand the results, analyze the patterns, trends and potential problems contained in the heating network equipment data, apply the analysis results to the operation optimization, fault diagnosis and energy consumption management of the heating network equipment, and formulate corresponding strategies and measures.

Images