Intelligent heat supply internet-of-things regulation and control system

Abstract

The invention discloses an intelligent heat supply internet-of-things regulation and control system, relates to the technical field of heat supply internet-of-things regulation and control, and aims at solving the problems that a traditional system is low in regulation and control precision, poor in efficiency and free of a closed-loop link. The system comprises a sensing layer, a network layer, a platform layer and an application layer which are in communication connection in sequence to form a data closed-loop regulation and control link. The sensing layer collects heat data through multiple types of sensors, and an edge calculation module performs denoising and pre-regulation and control; the network layer adopts optical fiber transmission, and security is guaranteed by combining encryption, authentication and CRC32 verification; the platform layer processes data by means of cloud computing storage, predicts 24-hour load and identifies abnormity by means of a regression algorithm, and visually displays the data; and the application layer automatically adjusts the heat source power and the pipe network flow, locates faults within 10 seconds, pushes a maintenance scheme, supports user-defined peak-valley heat supply and parameter query feedback, and realizes efficient, accurate and low-consumption heat supply.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of heat supply Internet of Things regulation system, in particular to an intelligent heat supply Internet of Things regulation system. BACKGROUND

[0002] At present, as a core component of urban infrastructure, the energy efficiency and environmental performance of the heat supply system have become key factors for the sustainable development of cities. Although the existing intelligent heat supply system integrates basic regulation means, it still has significant technical bottlenecks due to the limitations of traditional technical architecture. On the one hand, the balance regulation of conventional intelligent heat supply systems relies on comprehensive data centers, which are not optimized for the real-time and multi-source characteristics of heat supply data, resulting in low data processing efficiency and ultimately high average absolute percentage error of balance regulation results, making it difficult to meet user heating demand and system energy saving requirements. On the other hand, traditional regulation methods are easily affected by external environmental and internal system interference factors, resulting in deviations in regulation results, which in turn leads to high energy consumption, unstable pipe network operation, and uneven user end room temperature, making it difficult to adapt to the core needs of modern cities for "efficient, accurate, and low-consumption" intelligent heat supply systems.

[0003] Internet of Things technology has the potential to break through the above technical bottlenecks due to its advantages in multi-node sensing, real-time data transmission, and distributed processing. Although there have been attempts to apply Internet of Things technology to heat supply systems in existing technologies, they mostly focus on data collection at a single level and do not build a "sensing-transmission-processing-regulation-feedback" full-link closed-loop system. Moreover, there is a lack of specialized design for hierarchical data processing, dynamic load prediction, and precise fault positioning in heat supply systems, resulting in the underutilization of the application value of Internet of Things technology and the inability to fundamentally solve the regulation efficiency and accuracy problems of traditional intelligent heat supply systems. SUMMARY

[0004] The present application aims to provide an intelligent heat supply Internet of Things regulation system to solve the problems raised in the background.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical solution: an intelligent heat supply Internet of Things regulation system, comprising a sensing layer, a network layer, a platform layer, and an application layer, which are sequentially connected in communication to form a data closed-loop regulation link; The sensing layer includes multiple types of sensors deployed in the heat source, pipe network, heat exchange station, and user end of the heat supply system, as well as edge computing modules electrically connected to the sensors. The sensors collect heat supply temperature, pressure, flow, and heat data, and the edge computing modules preliminarily denoise and clean the raw data and pre-regulate according to the preset threshold. The network layer transmits data by wired or wireless communication, and guarantees the security of data and control instructions by encryption algorithm and identity authentication protocol; The platform layer is based on a cloud computing platform, and stores, standardizes, and predicts heat supply load and identifies pipe network abnormalities for the transmitted data, and visualizes heat supply data; The application layer automatically adjusts heat supply parameters according to the analysis results of the platform layer, generates pipe network fault positioning and cause reports, and also provides an interface for users to query parameters, customize heat supply settings, and feedback information.

[0006] Further, the multiple types of sensors of the perception layer include temperature sensors, pressure sensors, flow sensors, and heat meters.

[0007] Further, the wired communication mode of the network layer uses optical fiber transmission, and the wireless communication mode uses low-power wide-area network technology, which is suitable for heat supply scenarios with scattered equipment distribution and low-frequency stable communication requirements.

[0008] Further, the analysis and prediction module of the platform layer uses a regression analysis algorithm to construct a correlation model of heat supply load and meteorological conditions, and predicts the heat supply load change trend in the next 24 hours through historical load data and real-time meteorological data.

[0009] Further, the intelligent regulation and control module of the application layer automatically increases the heat source output power by 10% to 20% and optimizes pipe network flow distribution to balance regional heat supply differences during winter cold wave periods according to the high heat supply load data predicted by the platform layer.

[0010] Further, the edge computing module of the perception layer uses a mean filter algorithm to remove pulse noise in the original data during preliminary data processing, and the pre-regulation threshold is dynamically adjusted according to the energy consumption average difference of the current operation period of the heat supply system.

[0011] Further, the visualization interaction module of the platform layer supports displaying pipe network temperature distribution in the form of a heat map and energy consumption change curve of the heat source station in the past 7 days in the form of a line chart, and supports management personnel to export energy consumption reports through the interface.

[0012] Further, the fault early warning and diagnosis module of the application layer generates fault positioning information within 10 seconds after identifying abnormal pipe network data, with a positioning accuracy error of not more than 5 m, and synchronously pushes an emergency treatment scheme including blockage investigation and leakage repair steps to the operation and maintenance terminal.

[0013] Further, the interaction module supports users to set a "peak-valley period custom heat supply" mode, automatically maintains the preset temperature during the heat peak period, and reduces the temperature by 2-3°C during the non-peak period to achieve energy saving.

[0014] Compared with the prior art, the beneficial effects of the present invention are: This intelligent heating IoT control system achieves high-precision and real-time acquisition of heating data through multiple types of sensors with preset parameters in the sensing layer. Combined with the platform layer regression analysis algorithm for accurate prediction of heating load and the cluster analysis algorithm for rapid identification of pipeline anomalies, compared with traditional data-driven control methods and pipeline resistance identification control methods, it can significantly reduce the MAPE value of balance control at different times, ensuring that the control results are more in line with actual heating needs and reducing room temperature fluctuations at the user end.

[0015] The system constructs a closed-loop control link of "perception layer - network layer - platform layer - application layer". The edge computing module of the perception layer can perform preliminary noise reduction and pre-control of the raw data to reduce the pressure of invalid data transmission; the platform layer is based on a distributed storage and processing framework of cloud computing to improve data processing efficiency; the intelligent control module of the application layer can dynamically adjust the heat source power and pipeline flow according to the load forecast results.

[0016] The network layer ensures the security of data transmission and control commands through encryption algorithms and identity authentication protocols, preventing data leakage or malicious manipulation. The application layer fault early warning and diagnosis module can locate pipeline faults within 10 seconds and push emergency handling solutions, significantly shortening fault investigation and maintenance time and reducing the risk of system downtime. The platform layer visualization and interaction module intuitively displays pipeline temperature and energy consumption changes in the form of heat maps, line graphs, etc., and supports one-click report export, providing managers with clear decision-making basis and simplifying operation and maintenance processes. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the system flow of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] See Figure 1 The present invention provides a technical solution: an intelligent heating Internet of Things control system, comprising a sensing layer, a network layer, a platform layer and an application layer, wherein the sensing layer, network layer, platform layer and application layer are sequentially connected to form a data closed-loop control link; The sensing layer includes various types of sensors deployed in the heat source, pipe network, heat exchange station and user end of the heating system, as well as an edge computing module electrically connected to the sensors. The sensors collect heating temperature, pressure, flow rate and heat data. The edge computing module performs preliminary noise removal and cleaning on the raw data and pre-adjusts it according to preset thresholds. Temperature sensors should be deployed every 500 meters in the pipeline network, and at least one in each room at the user end; pressure sensors should be installed before and after the pipeline valves and at the outlet of the heat source station; flow sensors should be installed in conjunction with heat meters to ensure synchronous data collection.

[0020] In addition to mean filtering for noise reduction, a new outlier removal algorithm has been added. When the collected data exceeds the normal range, it is automatically marked and temporarily stored to avoid interfering with control decisions.

[0021] The sensor response time must be ≤1.5s, the measurement accuracy error must not exceed ±0.5℃ and ±0.02MPa, and the intelligent valve adjustment accuracy must reach ±5% opening degree; The network layer uses wired or wireless communication to transmit data, and uses encryption algorithms and authentication protocols to ensure the security of data and control commands. In long-distance scenarios such as urban main road pipeline networks, LoRa low-power wide area network technology is adopted, with a communication distance coverage of 1-3km; in data-intensive areas such as heat source stations and heat exchange stations, fiber optic wired transmission is used, with bandwidth ≥100Mbps and latency ≤10ms.

[0022] In addition to encryption algorithms and identity authentication, a new data transmission integrity check has been added, using a CRC32 checksum to ensure that the data has not been tampered with; device access requires two-way authentication, and unauthorized devices are prohibited from accessing the network.

[0023] The platform layer is based on a cloud computing platform, which stores massive amounts of transmitted data, processes them in a standardized manner, predicts heating load and identifies pipeline anomalies through algorithms, and visualizes heating data. The regression analysis algorithm uses a linear regression model. The input parameters include outdoor temperature, wind speed, sunshine duration and historical load data. The prediction step size is set to 1 hour, and the load prediction error for the next 24 hours must be ≤8%.

[0024] Historical data is stored using a distributed database with a retention period of ≥2 years; cloud computing nodes have ≥32 CPU cores and ≥128GB of memory to meet the requirement of processing 100,000 data entries per second.

[0025] The application layer includes an intelligent control module, a fault early warning and diagnosis module, and a user interaction module. The intelligent control module communicates with the analysis and prediction module of the platform layer and automatically adjusts the output power of the heat source, the distribution of pipeline flow, and the heating temperature at the user end based on the heating load prediction results and real-time energy consumption data. The fault early warning and diagnosis module receives pipeline anomaly data identified by the platform layer, generates fault location information and fault cause analysis reports, and triggers corresponding emergency handling instructions. The user interaction module provides a mobile or PC interface, supports users to query heating parameters, customize heating periods and temperatures, and receives user feedback information and transmits it to the platform layer.

[0026] The sensing layer contains various types of sensors, including temperature sensors, pressure sensors, flow sensors, and heat meters.

[0027] After a fault warning is issued, the system automatically generates a repair work order, which includes fault location navigation and a list of required spare parts. If the fault affects the user's heating, an apology message and the estimated recovery time will be automatically pushed to the user's mobile device.

[0028] The network layer uses fiber optic transmission for wired communication and low-power wide area network technology for wireless communication, making it suitable for heating scenarios where devices are distributed in a dispersed manner and communication needs are low-frequency and stable.

[0029] The platform layer's analysis and prediction module uses regression analysis algorithms to construct a correlation model between heating load and meteorological conditions, and uses historical load data and real-time meteorological data to predict the trend of heating load changes in the next 24 hours.

[0030] Collect data on building types, areas, and aging of pipe networks in the heating area, and formulate deployment plans for sensors and communication equipment.

[0031] Prioritize the deployment of heat source stations and main pipeline equipment, and complete the platform layer construction and testing; then promote the installation of user-end equipment and simultaneously debug application layer functions.

[0032] The system is considered to be qualified if it runs continuously for 72 hours, with a data acquisition success rate of ≥99%, a control response time of ≤30s, and a fault location error of ≤5m.

[0033] During cold spells in winter, the intelligent control module at the application layer automatically increases the output power of the heat source by 10% to 20% based on the high heating load data predicted by the platform layer, and optimizes the distribution of pipeline flow to balance regional heating differences.

[0034] During the initial data processing, the edge computing module of the perception layer uses a mean filtering algorithm to remove impulse noise from the original data, and the pre-regulation threshold is dynamically adjusted according to the average energy consumption difference of the heating system during the current operating period.

[0035] The platform layer's visualization and interaction module supports displaying the network temperature distribution in the form of a heat map, displaying the energy consumption change curve of the heat source station in the form of a line graph over the past 7 days, and allows managers to export energy consumption reports with one click through the interface.

[0036] After identifying abnormal data in the pipeline network, the application layer's fault early warning and diagnosis module generates fault location information within 10 seconds, with a location accuracy error of no more than 5 meters. Simultaneously, it pushes an emergency handling plan, including blockage investigation and leak repair steps, to the operation and maintenance terminal.

[0037] The interactive module allows users to set a "peak and off-peak time custom heating" mode, which automatically maintains the preset temperature during peak heating periods and lowers it by 2-3℃ during off-peak periods to achieve energy saving.

Claims

1. A smart heating Internet of Things (IoT) control system, characterized in that, It includes a perception layer, a network layer, a platform layer, and an application layer, which are sequentially connected to form a data closed-loop control link. The sensing layer includes various types of sensors deployed in the heat source, pipe network, heat exchange station and user end of the heating system, as well as an edge computing module electrically connected to the sensors. The sensors collect heating temperature, pressure, flow rate and heat data. The edge computing module performs preliminary noise removal and cleaning on the raw data and pre-adjusts it according to preset thresholds. The network layer uses wired or wireless communication to transmit data, and uses encryption algorithms and authentication protocols to ensure the security of data and control commands. The platform layer is based on a cloud computing platform, which stores massive amounts of transmitted data, processes it in a standardized manner, predicts heating load and identifies pipeline anomalies through algorithms, and visualizes heating data. The application layer automatically adjusts heating parameters based on the analysis results of the platform layer, generates pipeline fault location and cause reports, and provides an interface to support users in querying parameters, customizing heating settings, and providing feedback information.

2. The intelligent heating IoT control system according to claim 1, characterized in that, The sensing layer includes various types of sensors such as temperature sensors, pressure sensors, flow sensors, and heat meters.

3. The intelligent heating IoT control system according to claim 1, characterized in that, The network layer uses fiber optic transmission for wired communication and low-power wide area network technology for wireless communication, making it suitable for heating scenarios where devices are distributed in a dispersed manner and communication needs are low-frequency and stable.

4. The intelligent heating IoT control system according to claim 1, characterized in that, The analysis and prediction module of the platform layer uses regression analysis algorithm to construct a correlation model between heating load and meteorological conditions, and predicts the trend of heating load change in the next 24 hours through historical load data and real-time meteorological data.

5. The intelligent heating IoT control system according to claim 1, characterized in that, During cold spells in winter, the intelligent control module at the application layer automatically increases the output power of the heat source by 10% to 20% based on the high heating load data predicted by the platform layer, and optimizes the distribution of pipeline flow to balance regional heating differences.

6. The intelligent heating IoT control system according to claim 1, characterized in that, During the initial data processing, the edge computing module of the perception layer uses a mean filtering algorithm to remove impulse noise from the original data, and the pre-regulation threshold is dynamically adjusted according to the average energy consumption difference of the heating system during the current operating period.

7. The intelligent heating IoT control system according to claim 1, characterized in that, The visualization and interaction module of the platform layer supports displaying the temperature distribution of the pipeline network in the form of a heat map, displaying the energy consumption change curve of the heat source station in the form of a line graph over the past 7 days, and supporting managers to export energy consumption reports with one click through the interface.

8. The intelligent heating IoT control system according to claim 1, characterized in that, After identifying abnormal data in the pipeline network, the fault early warning and diagnosis module of the application layer generates fault location information within 10 seconds with a location accuracy error of no more than 5m, and simultaneously pushes an emergency handling plan including blockage investigation and leakage repair steps to the operation and maintenance terminal.

9. The intelligent heating IoT control system according to claim 1, characterized in that, The interactive module supports users to set a "peak and off-peak time custom heating" mode, which automatically maintains the preset temperature during peak heating periods and lowers it by 2-3°C during off-peak periods to achieve energy saving.

Images