Intelligent monitoring and early warning system for condensate water of heating and ventilation system based on Internet of Things

Abstract

The invention relates to the technical field of leakage detection, in particular to a heating and ventilation system condensate water intelligent monitoring and early warning system based on the Internet of Things, which comprises a spectrum sensing scheduling module, a data transmission optimization module, a vibration pressure monitoring module, a gas component analysis module and a leakage early warning module. According to the invention, the wireless spectrum bandwidth is dynamically scheduled, the data transmission time sequence is optimized, the priority transmission of key monitoring data is ensured, the timeliness and accuracy are improved, the data loss caused by interference and unstable signals is reduced, the vibration and pressure sensor analysis are combined, the leakage is identified in real time, and the leakage position and trend are determined through gas component monitoring; comprehensive risk analysis is provided, sensitivity and accuracy are improved, evaluation of environmental changes is enhanced through temperature and humidity sensing, the monitoring and early warning functions are further improved, manual intervention is reduced, the autonomous monitoring and alarm capacity of equipment is improved, and resource use and early warning response speed is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of leakage detection, and in particular to an intelligent monitoring and early warning system for condensed water in a heating and ventilation system based on the Internet of Things. Background Art

[0002] The field of leak detection technology includes technical means for monitoring, identifying and warning of leaks in pipelines, containers, equipment and related fluid transportation systems. The core content of this technical field includes leak monitoring sensors, data acquisition and analysis, remote monitoring and early warning systems, etc. Leak detection relies on pressure change detection, flow balance analysis, acoustic signal analysis, optical imaging detection and gas sensing technology to evaluate the integrity of the target system in real time or regularly. Leak detection technology is widely used in water supply networks, oil and gas pipelines, chemical equipment, HVAC systems and other industries. It uses a variety of physical and chemical detection methods and intelligent analysis methods to achieve rapid identification and early warning of leaks.

[0003] Among them, the intelligent monitoring and early warning system for condensate water in HVAC systems based on the Internet of Things refers to a system that uses sensor networks, wireless communications and data analysis technologies to monitor the condensate discharge in HVAC systems and provide abnormal early warnings. It targets condensate leakage and abnormal discharge problems, and covers technical matters such as flow monitoring, conductivity detection, liquid level measurement, and temperature and humidity perception. Specifically, flow sensors and conductivity sensors are arranged at key positions in the condensate drainage pipeline to detect water flow changes and water quality characteristics, and liquid level sensors are used to monitor the height of accumulated water. At the same time, temperature and humidity sensors are used to perceive changes in environmental conditions. The data is uploaded to the remote server via wireless communication, and real-time comparison and analysis are performed using the set monitoring rules. The threshold is used to determine whether to trigger an early warning signal.

[0004] The existing leak detection technology relies on sensors and analysis systems to collect and compare data in real time. However, in actual operation, the transmission frequency, timing control and data accuracy are limited by many factors, resulting in the inability to capture early leakage signals in a timely and accurate manner. For example, frequency band interference occurs during signal transmission, especially when multiple monitoring points in the pipeline system work simultaneously, which is prone to data loss or transmission delay, affecting the overall system's responsiveness. The traditional system is insufficient in the joint analysis of multi-dimensional signals such as pipeline pressure and vibration, and can only monitor a single indicator, lacking a comprehensive assessment of leakage risks. The abnormal manifestation of condensate leakage is the coexistence of multiple physical phenomena. The existing technology is relatively simple in processing multi-dimensional signals, resulting in the inability to fully capture potential risks in complex environments. The limitations of gas composition analysis are also another shortcoming of the existing technology, making it difficult to provide sufficiently accurate leakage location determination and trend prediction, thereby delaying the early warning and response of the leakage. The existing technology is not sensitive enough to the dynamic changes, missing the best alarm time, and bringing unnecessary difficulties and risks to maintenance and emergency treatment. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent monitoring and early warning system for condensate water in a HVAC system based on the Internet of Things.

[0006] In order to achieve the above purpose, the present invention adopts the following technical solution: The intelligent monitoring and early warning system for condensed water in HVAC system based on the Internet of Things includes:

[0007] The spectrum sensing scheduling module extracts the spectrum density of the condensate monitoring node based on the signal strength value, signal-to-noise ratio value, and interference index value of the HVAC pipeline sensor, screens the available frequency bands of the HVAC data gateway, and obtains the spectrum scheduling allocation value;

[0008] The data transmission optimization module extracts HVAC data gateway data based on the spectrum scheduling allocation value, analyzes the condensate monitoring data transmission priority, adjusts the transmission timing of the HVAC data gateway, and obtains a condensate data transmission parameter set;

[0009] The vibration pressure monitoring module calls the condensate data transmission parameter set, extracts the vibration signal of the pipeline vibration sensor and the pressure signal of the condensate pressure sensor, identifies the vibration offset and the pressure fluctuation index, and obtains the condensate pipe pressure state parameter;

[0010] The gas composition analysis module extracts the gas concentration value, humidity value, and temperature value of the condensed water detection based on the condenser pressure state parameter, analyzes the abnormality of the gas content in the condensed water, and obtains a gas monitoring parameter set;

[0011] The leakage warning module predicts and analyzes the leakage location and leakage trend based on the gas monitoring parameter set, identifies the risk of condensate leakage and issues a warning, and obtains a real-time warning result of condensate leakage.

[0012] As a further scheme of the present invention, the spectrum scheduling allocation value includes frequency band selection, signal strength threshold, signal-to-noise ratio parameter, and interference index; the condensate data transmission parameter set includes transmission priority, data flow, timing adjustment parameters, and throughput index; the condenser pressure state parameters include vibration amplitude, pressure fluctuation amplitude, and leakage level; the gas monitoring parameter set includes gas concentration, ambient humidity, temperature parameters, and leakage gas composition; the real-time warning result of condensate leakage includes leakage location, leakage trend, and risk level.

[0013] As a further solution of the present invention, the spectrum sensing scheduling module includes:

[0014] The signal parameter calculation submodule calculates the signal interference correction index based on the signal strength value, signal-to-noise ratio value, and interference index value of the HVAC pipe sensor using the formula:

[0015] ;

[0016] Normalize the HVAC pipe sensor data to obtain normalized signal parameter values;

[0017] in, represents the signal interference correction index, Represents the signal strength value, represents the signal-to-noise ratio value, represents the interference index value, represents the interference threshold;

[0018] The spectrum density extraction submodule calculates the spectrum density of the condensate monitoring node based on the normalized signal parameter value, identifies the distribution of the spectrum density through the integral operation of the signal power, and obtains the spectrum density value of the condensate monitoring node;

[0019] The frequency band screening and scheduling submodule calls the spectrum density value of the condensate monitoring node, screens the available frequency bands of the HVAC data gateway, analyzes the spectrum occupancy rate and interference distribution adaptability, and generates a spectrum scheduling allocation value.

[0020] As a further solution of the present invention, the data transmission optimization module includes:

[0021] The data extraction submodule extracts data from the HVAC data gateway based on the spectrum scheduling allocation value, filters the condensate monitoring related data, analyzes the data type and transmission rate, and establishes a condensate monitoring data set;

[0022] The transmission priority calculation submodule calls the condensate monitoring data set, analyzes the criticality and delay sensitivity of the data, sets the data delay threshold, and uses the formula:

[0023] ;

[0024] Calculate the condensate water data transmission priority value;

[0025] in, Represents the condensate data transmission priority value, Represents the data refresh rate, Represents the delay sensitivity of the current data, represents the delay sensitivity threshold, Represents the queuing time of data in the queue, Represents the length of the data packet;

[0026] The transmission timing adjustment submodule calls the condensed water data transmission priority value, adjusts the transmission timing of the HVAC data gateway, optimizes the data queue order according to the priority, and generates a condensed water data transmission parameter set.

[0027] As a further solution of the present invention, the vibration pressure monitoring module comprises:

[0028] The signal acquisition submodule calls the condensate data transmission parameter set, extracts the vibration signal of the pipeline vibration sensor and the pressure signal of the condensate pressure sensor, analyzes the vibration amplitude, vibration frequency and pressure change rate, and obtains the vibration pressure signal set;

[0029] The vibration and pressure calculation submodule sets the vibration offset reference based on the vibration pressure signal set, using the formula:

[0030] ;

[0031] The vibration offset value is calculated and combined with the pipeline condensate pressure signal to analyze the fluctuation situation, and the pressure change rate is compared with the pressure stability threshold to obtain the pressure fluctuation index;

[0032] in, Represents the vibration offset value, represents the amplitude of the vibration signal, represents the measured vibration signal frequency, represents the vibration reference frequency, Represents the time duration value of the vibration signal, Representative The noise interference amount of the interfering data points, is the total number of interference data points;

[0033] The condenser pressure state identification submodule calls the vibration offset value and the pressure fluctuation index, analyzes the pipeline vibration characteristics and the pressure distribution pattern, determines the condenser pressure state, matches the abnormal vibration and abnormal pressure fluctuation relationship, and obtains the condenser pressure state parameters.

[0034] As a further solution of the present invention, the gas composition analysis module comprises:

[0035] The gas data acquisition submodule extracts the gas concentration value, humidity value and temperature value in the condenser based on the condenser pressure state parameter, analyzes the gas type and concentration change trend, and obtains the gas characteristic parameter set;

[0036] The gas anomaly calculation submodule sets the normal leakage threshold based on the gas characteristic parameter set, analyzes the gas leakage mode in combination with the change characteristics of the differentiated gas, determines the correlation between gas concentration and humidity and temperature, and identifies the abnormal fluctuation trend, using the formula:

[0037] ;

[0038] Calculate and obtain the abnormal index of condenser gas;

[0039] in, Represents the abnormal index of condenser gas. Represents the gas concentration value, Represents the humidity of the monitoring area. Represents the base humidity, Represents the current ambient temperature. represents the gas diffusion rate;

[0040] The condenser gas monitoring submodule calls the condenser gas anomaly index, analyzes the abnormal gas concentration in the condensate water abnormal area, screens the gas abnormal fluctuation value, matches the gas type, and generates a gas monitoring parameter set.

[0041] As a further solution of the present invention, the leakage warning module includes:

[0042] The leakage trend analysis submodule analyzes the leakage gas concentration change trend, analyzes the leakage diffusion rate, sets the leakage trend reference value, and obtains the leakage trend parameter set based on the gas monitoring parameter set;

[0043] The leakage risk identification submodule sets the risk identification threshold based on the leakage trend parameter set, using the formula:

[0044] ;

[0045] Combined with the gas data of differentiated areas, the risk level of condensate leakage is analyzed and the leakage risk index is calculated;

[0046] in, represents the leakage risk index, Represents the current gas concentration, represents the leakage reference concentration, represents the gas diffusion rate, represents the diffusion time interval, Represents the current ambient humidity. Represents the baseline humidity in the leak area, Represents the number of diffusion calculation steps;

[0047] The intelligent early warning submodule calls the leakage risk index, analyzes the condensate leakage risk level, screens the risk exceeding limit value, matches the leakage trend characteristics, and generates a real-time early warning result for condensate leakage.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are:

[0049] In the present invention, the spectrum bandwidth of wireless transmission is dynamically scheduled to optimize the transmission timing of condensate data, ensure the priority transmission of key monitoring data, improve the timeliness and accuracy of information processing, better adapt to the signal quality differences between different monitoring points in the pipeline, avoid data loss or transmission delays due to interference or signal instability, and combine the signal analysis of vibration and pressure sensors to effectively capture the slight changes in pipeline vibration and condensate pressure fluctuations, so as to identify potential leakage problems in real time, and further confirm the leakage location and trend through the monitoring of gas composition, provide a comprehensive leakage risk analysis, improve the sensitivity and accuracy of detection, and be able to quickly respond to abnormal situations in actual applications, give early warnings and avoid catastrophic consequences. The dynamic perception of temperature and humidity changes enables the system to accurately assess the impact of environmental conditions on leakage risks, thereby further improving the overall monitoring and early warning functions, which can not only reduce manual intervention, but also significantly improve the equipment's autonomous monitoring and alarm capabilities, and optimize resource utilization efficiency and early warning response speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a system flow chart of the present invention;

[0051] Figure 2 This is a flowchart of obtaining the spectrum sensing scheduling module in the present invention;

[0052] Figure 3 This is a flowchart of obtaining the data transmission optimization module in the present invention;

[0053] Figure 4 This is a flow chart for obtaining the vibration pressure monitoring module in the present invention;

[0054] Figure 5 This is a flow chart of obtaining the gas composition analysis module in the present invention;

[0055] Figure 6 This is a flow chart for obtaining the leakage warning module in the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0057] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions 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 orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0058] See also Figure 1 The intelligent monitoring and early warning system for condensed water in HVAC systems based on the Internet of Things includes:

[0059] The spectrum sensing scheduling module extracts the spectrum density of the condensate monitoring node based on the signal strength value, signal-to-noise ratio value, and interference index value of the HVAC pipeline sensor, screens the available frequency bands of the HVAC data gateway, and obtains the spectrum scheduling allocation value;

[0060] The data transmission optimization module extracts HVAC data gateway data based on the spectrum scheduling allocation value, analyzes the condensate monitoring data transmission priority, adjusts the transmission timing of the HVAC data gateway, and obtains the condensate data transmission parameter set;

[0061] The vibration pressure monitoring module calls the condensate data transmission parameter set, extracts the vibration signal of the pipeline vibration sensor and the pressure signal of the condensate pressure sensor, identifies the vibration offset and pressure fluctuation index, and obtains the condensate pipe pressure state parameter;

[0062] The gas composition analysis module extracts the gas concentration value, humidity value, and temperature value of the condensed water detection based on the condenser pressure state parameters, analyzes the abnormality of the gas content in the condensed water, and obtains the gas monitoring parameter set;

[0063] The leakage warning module predicts and analyzes the leakage location and leakage trend based on the gas monitoring parameter set, identifies the risk of condensate leakage and issues a warning, and obtains real-time warning results for condensate leakage.

[0064] The spectrum scheduling allocation values ​​include frequency band selection, signal strength threshold, signal-to-noise ratio parameters, and interference index. The condensate data transmission parameter set includes transmission priority, data flow, timing adjustment parameters, and throughput indicators. The condenser pressure state parameters include vibration amplitude, pressure fluctuation amplitude, and leakage level. The gas monitoring parameter set includes gas concentration, ambient humidity, temperature parameters, and leakage gas composition. The real-time warning results of condensate leakage include leakage location, leakage trend, and risk level.

[0065] See also Figure 2 ,The spectrum sensing scheduling module includes;

[0066] The signal parameter calculation submodule calculates the signal interference correction index based on the signal strength value, signal-to-noise ratio value, and interference index value of the HVAC pipe sensor using the formula:

[0067] ;

[0068] Normalize the HVAC pipe sensor data to obtain normalized signal parameter values;

[0069] in, represents the signal interference correction index, Represents the signal strength value, represents the signal-to-noise ratio value, represents the interference index value, represents the interference threshold;

[0070] First, the signal strength value ( ) can be measured directly by sensors. For example, in HVAC ducts, the sensor detects a signal strength of 0.8 watts and a signal-to-noise ratio of ( ) represents the ratio of signal power to noise power, which can be obtained by measuring the power of the signal and noise and calculating their ratio. Assuming that the measured signal power is 0.8 watts and the noise power is 0.2 watts, the signal-to-noise ratio is 4 (i.e. ), interference index value ( ) reflects the degree of interference in the environment, which can be obtained by analyzing the interference components in the signal spectrum. Assuming the interference index is 0.3, the interference threshold is set ( ) is 0.2, indicating the maximum acceptable interference level of the system, and the signal interference correction index is calculated ( ), using the formula:

[0071] ;

[0072] Substituting the above values, we get:

[0073] ;

[0074] The correction index is used to normalize the sensor data. Normalization is to adjust the data to a specific range of 0 to 1 to eliminate the influence of different dimensions. For example, the measured signal strength of 0.8 watts is divided by the maximum signal strength of 1 watt to obtain a normalized signal strength of 0.8. Combined with the signal interference correction index, the normalized signal is adjusted. Assuming that the normalized signal strength is 0.8 and the signal interference correction index is 0.38, the normalized signal parameter value is the product of the two, that is, 0.8×0.38=0.304, and the normalized signal parameter value is obtained.

[0075] The spectrum density extraction submodule calculates the spectrum density of the condensate monitoring node based on the normalized signal parameter value, identifies the distribution of the spectrum density through the integral operation of the signal power, and obtains the spectrum density value of the condensate monitoring node;

[0076] The signal power integration operation is used to obtain the spectral density distribution, the normalized signal parameter value is Fourier transformed to obtain its spectral representation, the spectrum is squared to obtain the power spectral density, the power spectral density is integrated within the frequency range of interest to obtain the spectral density value, assuming that the power at a specific frequency after Fourier transformation is 0.5 watts, then the spectral density is 0.5 watts·Hz, and the spectral density value of the condensate monitoring node is obtained.

[0077] The frequency band screening and scheduling submodule calls the spectrum density value of the condensate monitoring node, screens the available frequency bands of the HVAC data gateway, analyzes the spectrum occupancy rate and interference distribution adaptability, and generates spectrum scheduling allocation values;

[0078] Calculate the compatibility between spectrum occupancy and interference distribution, set a spectrum occupancy threshold, for example 70%, which means that when the occupancy of a certain frequency band is lower than 70%, the frequency band is considered available, analyze the interference distribution of each frequency band, and calculate its compatibility with the acceptable interference level of the system. Assuming that the occupancy of a certain frequency band is 60% and the interference level is lower than the set interference threshold, the frequency band is considered suitable for use, select the optimal frequency band, and obtain the spectrum scheduling allocation value.

[0079] See also Figure 3 ,The data transmission optimization module includes;

[0080] The data extraction submodule extracts data from the HVAC data gateway based on the spectrum scheduling allocation value, filters the condensate monitoring related data, analyzes the data type and transmission rate, and establishes the condensate monitoring data set;

[0081] First, the data types stored in the data gateway are analyzed, and the data records related to condensate water monitoring are extracted. The HVAC data gateway stores multiple types of data, including ambient temperature, humidity, air flow rate, and condensate water flow data. During the data extraction process, it is necessary to identify the data frame structure and determine the storage location and format of the condensate water data. For example, the data frame format stored in a gateway includes data identifiers, timestamps, numerical data, error correction information, etc. During extraction, the data identifier is used to filter the relevant data. Assuming that the data identifier is 0010, which represents condensate water monitoring data, the data frame with identifier 0010 is filtered and the numerical data therein is read. The transmission rate of the data is further analyzed. Assuming that the data frame is updated once per second, the data transmission rate is 1Hz. If the data update frequency is increased to 10Hz, it means that data is received 10 times per second. The extracted data is formatted to make it suitable for subsequent analysis, and a condensate water monitoring data set is constructed. The data set contains information such as transmission time, data category, and data value.

[0082] The transmission priority calculation submodule calls the condensate monitoring data set, analyzes the criticality and delay sensitivity of the data, and sets the data delay threshold using the formula:

[0083] ;

[0084] Calculate the condensate water data transmission priority value;

[0085] in, Represents the condensate data transmission priority value, Represents the data refresh rate, Represents the delay sensitivity of the current data, represents the delay sensitivity threshold, Represents the queuing time of data in the queue, Represents the length of the data packet;

[0086] First, the importance of data can be evaluated by calculating the rate of change of the data. If the change in the condensate flow data in the past five minutes is greater than the set change threshold, the data is marked as high priority data. For example, if the change threshold is set to 5%, if the measured condensate flow changes from 2.0L / min to 2.2L / min within five minutes, the change rate is , exceeds the threshold, so the priority is higher. Calculate the delay sensitivity of the data. Assuming that the standard transmission delay threshold of condensed water data is 2 seconds, if the transmission delay of a data packet exceeds this value, its priority needs to be adjusted. The formula is:

[0087] ;

[0088] in, Represents the data refresh rate, assuming it is 5Hz, Represents the delay sensitivity of the current data. If the current data transmission delay is 3 seconds, then , represents the delay sensitivity threshold, set to 2 seconds, Represents the queuing time of data in the queue, set to 0.5 seconds, Represents the length of the data packet, set to 256 bytes, and substitute into the calculation:

[0089] ;

[0090] Get the condensate data transmission priority value. The higher the data priority value, the faster the data needs to be transmitted.

[0091] The transmission timing adjustment submodule calls the condensed water data transmission priority value, adjusts the transmission timing of the HVAC data gateway, optimizes the data queue order according to the priority, and generates a condensed water data transmission parameter set;

[0092] First, sort the data according to priority and set the transmission time interval. Assume that high-priority data needs to be transmitted within 1 second, while low-priority data can be delayed until 5 seconds. Calculate the expected transmission timing of different data packets. Assume that there are three data packets, of which data packet A has a priority of 0.08, data packet B has a priority of 0.05, and data packet C has a priority of 0.02. Then data packet A is sent first, followed by data packet B, and data packet C is sent last. Data transmission is performed according to the adjusted transmission queue, the scheduling order of data streams is optimized, and a condensed water data transmission parameter set is generated.

[0093] See also Figure 4 , the vibration pressure monitoring module includes;

[0094] The signal acquisition submodule calls the condensate data transmission parameter set, extracts the vibration signal of the pipeline vibration sensor and the pressure signal of the condensate pressure sensor, analyzes the vibration amplitude, vibration frequency and pressure change rate, and obtains the vibration pressure signal set;

[0095] First, vibration sensors are installed at key positions of the pipeline, such as support points, bending parts or valve connections. They are mainly used to detect the vibration state of the pipeline. The main parameters of vibration signal acquisition include vibration amplitude, vibration frequency and instantaneous acceleration. Assuming that the amplitude detected by the vibration sensor is 0.05g and the acceleration is 0.3m / s2, the data needs to be analyzed in time series to analyze the fluctuation pattern of pipeline vibration. The condensate pressure sensor is installed at the low point or pressure mutation point of the pipeline. It is mainly used to measure the pressure of condensate flow. The parameters of pressure signal acquisition include instantaneous pressure value, pressure change rate and pressure duration. Assuming that the pressure measured by the condensate pressure sensor is 1.2MPa and the pressure change rate is 0.05MPa / s, it is necessary to further calculate its fluctuation in a short time, analyze the time synchronization of vibration signal and pressure signal, ensure data alignment, organize data format, and normalize parameters of different units for subsequent calculation to obtain vibration pressure signal set.

[0096] The vibration and pressure calculation submodule sets the vibration offset reference based on the vibration pressure signal set, using the formula:

[0097] ;

[0098] The vibration offset value is calculated and combined with the pipeline condensate pressure signal to analyze the fluctuation situation, and the pressure change rate is compared with the pressure stability threshold to obtain the pressure fluctuation index;

[0099] in, Represents the vibration offset value, represents the amplitude of the vibration signal, represents the measured vibration signal frequency, represents the vibration reference frequency, Represents the time duration value of the vibration signal, Representative The noise interference amount of the interfering data points, is the total number of interference data points;

[0100] First, the calculation of the vibration offset value needs to consider the degree of deviation of the vibration signal and set the vibration offset reference value. For example, the reference frequency of a pipeline during normal operation is 50Hz. If the currently measured vibration frequency is 55Hz, the vibration signal offset needs to be calculated to measure the degree of vibration change. The formula is:

[0101] ;

[0102] In which, it is assumed that the amplitude of the vibration signal The measured vibration signal frequency is 0.05g. The vibration reference frequency is 55Hz The duration of the vibration signal is 50Hz. For 2 seconds, the noise interference amount of vibration data According to different sampling point settings, assuming , each If they are 0.002, 0.003, and 0.001 respectively, then calculate:

[0103] ;

[0104] ;

[0105] ;

[0106] Obtain the vibration offset value and analyze its fluctuation in combination with the pipeline condensate pressure signal. Assuming that the pressure stability threshold is set to 0.1MPa, if the pressure fluctuation amplitude is greater than this value, the pressure fluctuation index increases. For example, if the condensate pressure changes from 1.2MPa to 1.4MPa within 10 seconds, the pressure change rate is calculated as MPa / s, which is less than the threshold value, so the fluctuation index maintains the normal range. The vibration offset value and the pressure fluctuation index are combined to determine the change trend for subsequent state identification and calculation of the pressure fluctuation index.

[0107] The condenser pressure state identification submodule calls the vibration offset value and pressure fluctuation index, analyzes the pipeline vibration characteristics and pressure distribution mode, determines the condenser pressure state, matches the abnormal vibration and abnormal pressure fluctuation relationship, and obtains the condenser pressure state parameters;

[0108] First, compare the historical vibration data of the pipeline, screen abnormal vibration values, and set the abnormal vibration threshold. For example, if the vibration offset value exceeds 0.1g, it is considered that there is an abnormal situation. Assuming that the calculated vibration offset value is 0.0806g, it does not exceed the threshold, and the current vibration state is within the normal range. At the same time, compare the pressure fluctuation index and screen abnormal pressure fluctuation values. Assuming that the pressure fluctuation index threshold is set to 0.03MPa / s, if the calculated pressure change rate is 0.02MPa / s, it does not exceed the set range. Match the relationship between abnormal vibration and abnormal pressure fluctuation. If abnormal vibration and abnormal pressure fluctuation occur at the same time, it is judged that the risk of condensate leakage is increased, and the pressure state parameters of the condenser are obtained.

[0109] See also Figure 5 ,The gas composition analysis module includes;

[0110] The gas data acquisition submodule extracts the gas concentration value, humidity value and temperature value in the condenser based on the condenser pressure state parameters, analyzes the gas type and concentration change trend, and obtains the gas characteristic parameter set;

[0111] First, gas samples are collected in the detection area, and multiple sensors are installed near the condensation water leakage point, including gas concentration sensors, temperature and humidity sensors, etc. The sensors are distributed at different heights and positions to ensure the integrity and accuracy of the data. Assume that 5 sensors are arranged in a certain area, 3 of which measure gas concentration and 2 measure temperature and humidity. The preliminary data obtained from the measurement include the concentration values ​​of CO2, H2O and O2, ambient temperature and relative humidity. When analyzing the data, it is necessary to perform denoising to remove abnormal data points. For example, at a certain time point, the CO2 concentration suddenly increases to 5000ppm, and the previous and subsequent values ​​are both around 400ppm. The data point is judged to be noise and is removed. The change trend of the data is further analyzed, and the concentration increase of different gas components is calculated. Assuming that the concentration of a gas increases from 200ppm to 500ppm within 10 minutes, the increase is , calculate the influence of temperature and humidity. Assuming that the temperature rises from 25℃ to 30℃ and the humidity increases from 40% to 50%, it indicates that there are large temperature and humidity fluctuations in the gas leakage area. Finally, all the data are integrated to construct a gas characteristic parameter set.

[0112] The gas anomaly calculation submodule sets the normal leakage threshold based on the gas characteristic parameter set, analyzes the gas leakage mode in combination with the change characteristics of differentiated gases, determines the correlation between gas concentration and humidity and temperature, and identifies abnormal fluctuation trends using the formula:

[0113] ;

[0114] Calculate and obtain the abnormal index of condenser gas;

[0115] in, Represents the abnormal index of condenser gas. Represents the gas concentration value, Represents the humidity of the monitoring area. Represents the base humidity, Represents the current ambient temperature. represents the gas diffusion rate;

[0116] First, calculate the change rate of the gas concentration value relative to the environment, set the background concentration baseline value, and assume that the normal concentration of O2 is 20.9%. If the monitored value drops to 19.5%, the concentration change rate is calculated as For humidity, the deviation between the humidity in the predicted leakage area and the environmental reference humidity is calculated. Assuming that the humidity in the monitoring area is 65% and the reference humidity is 50%, the deviation is 15%. The influence of ambient temperature is reflected by calculating the temperature increment. The standard ambient temperature is set to 25°C. If the current temperature is 30°C, the temperature increment is 5°C. Combining the above parameters, the formula is used:

[0117] ;

[0118] Among them, setting , , , , , substitute into the calculation:

[0119] ;

[0120] ;

[0121] The calculation is used to obtain the abnormal index of condenser gas, and the gas leakage pattern is analyzed in combination with the changing characteristics of different gases, the correlation between gas concentration and humidity and temperature is determined, and abnormal fluctuation trends are identified.

[0122] The condenser gas monitoring submodule calls the condenser gas anomaly index, analyzes the abnormal gas concentration in the condensate abnormal area, screens the gas abnormal fluctuation value, matches the gas type, and generates a gas monitoring parameter set;

[0123] First, filter the abnormal fluctuation value of gas leakage and set the abnormal threshold of gas leakage. Assume that the threshold is set to 25. If the calculated condenser gas abnormality index is 27.7, the gas is considered abnormal. Match the gas types and analyze the characteristic patterns of different gases when predicting leakage. For example, a sudden increase in CO2 concentration and a decrease in O2 concentration are related to pipeline leakage, while a sharp increase in humidity is related to the evaporation of condensed water. Combined with the data trends of each sensor, the predictability of gas leakage is identified and a gas monitoring parameter set is generated.

[0124] See also Figure 6 ,The leakage warning module includes;

[0125] The leakage trend analysis submodule analyzes the leakage gas concentration change trend, analyzes the leakage diffusion rate, sets the leakage trend baseline value, and obtains the leakage trend parameter set based on the gas monitoring parameter set;

[0126] First, obtain the gas data measured by different sensors, including the concentration values ​​of CO2, H2O, O2 and other components, as well as the temperature and humidity data of the leakage area. The data collection cycle is set to 10 minutes, and the changes of each gas at different time points are analyzed. Assuming that the CO2 concentration increases from 400ppm to 1000ppm within 10 minutes, the change rate is calculated as For humidity data, the base humidity is set to 50%. If the humidity detection value of the leakage area is 65%, the humidity deviation is , calculate the gas diffusion rate, set the initial gas concentration diffusion radius to 0.5m, and diffuse to 1.5m after 5 minutes, the calculated rate is , a leakage trend parameter set is generated based on all parameters.

[0127] The leakage risk identification submodule sets the risk identification threshold based on the leakage trend parameter set, using the formula:

[0128] ;

[0129] Combined with the gas data of differentiated areas, the risk level of condensate leakage is analyzed and the leakage risk index is calculated;

[0130] in, represents the leakage risk index, Represents the current gas concentration, represents the leakage reference concentration, represents the gas diffusion rate, represents the diffusion time interval, Represents the current ambient humidity. Represents the baseline humidity in the leak area, Represents the number of diffusion calculation steps;

[0131] First, compare the changes in gas concentration at different time points and calculate the leakage rate. Assuming that the gas concentration in the leakage area rises from 300ppm to 1200ppm within 10 minutes, and the reference gas change rate is set to 100ppm / min, the calculated leakage rate is If the calculated rate is lower than the reference rate, the leakage trend is considered to be slow. If it exceeds the reference rate, it is considered to be a high-risk leakage. The humidity change rate is calculated. The standard ambient humidity change is set to 5% / min. If the humidity in the leakage area rises from 40% to 60% within 5 minutes, the change rate is , using the formula:

[0132] ;

[0133] Set the current gas concentration , leakage reference concentration , gas diffusion rate , diffusion time , ambient humidity , reference humidity ,calculate:

[0134] ;

[0135] ;

[0136] The leakage risk index is calculated and used to identify the risk level of the leakage area and determine the severity of the leakage trend.

[0137] The intelligent early warning submodule calls the leakage risk index, analyzes the condensate leakage risk level, screens the risk exceeding limit value, matches the leakage trend characteristics, and generates the real-time early warning results of condensate leakage;

[0138] First, set the leakage risk level threshold. Assuming the high risk threshold is 900, if the calculated leakage risk index is 931, it is judged as a high-risk area. Compare the leakage trend parameters and calculate the fluctuation range of the leakage trend. Assuming that the fluctuation range of the leakage concentration changes by more than 50% within 30 minutes, it is judged as a sudden leakage. If the fluctuation range is less than 10%, it is judged as slow penetration. Combined with the characteristics of different leakage modes and matching the leakage area type, a real-time warning result for condensate leakage is generated.

[0139] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. The intelligent monitoring and early warning system for condensed water in HVAC system based on the Internet of Things is characterized by: The system comprises: The spectrum sensing scheduling module extracts the spectrum density of the condensate monitoring node based on the signal strength value, signal-to-noise ratio value, and interference index value of the HVAC pipeline sensor, screens the available frequency bands of the HVAC data gateway, and obtains the spectrum scheduling allocation value; The data transmission optimization module extracts HVAC data gateway data based on the spectrum scheduling allocation value, analyzes the condensate monitoring data transmission priority, adjusts the transmission timing of the HVAC data gateway, and obtains a condensate data transmission parameter set; The vibration pressure monitoring module calls the condensate data transmission parameter set, extracts the vibration signal of the pipeline vibration sensor and the pressure signal of the condensate pressure sensor, identifies the vibration offset and the pressure fluctuation index, and obtains the condensate pipe pressure state parameter; The gas composition analysis module extracts the gas concentration value, humidity value, and temperature value of the condensed water detection based on the condenser pressure state parameter, analyzes the abnormality of the gas content in the condensed water, and obtains a gas monitoring parameter set; The leakage warning module predicts and analyzes the leakage location and leakage trend based on the gas monitoring parameter set, identifies the risk of condensate leakage and issues a warning, and obtains a real-time warning result of condensate leakage.

2. The intelligent monitoring and early warning system for condensed water in HVAC system based on the Internet of Things according to claim 1 is characterized in that: The spectrum scheduling allocation value includes frequency band selection, signal strength threshold, signal-to-noise ratio parameter, and interference index; the condensate data transmission parameter set includes transmission priority, data flow, timing adjustment parameters, and throughput index; the condenser pressure state parameters include vibration amplitude, pressure fluctuation amplitude, and leakage level; the gas monitoring parameter set includes gas concentration, ambient humidity, temperature parameters, and leakage gas composition; the condensate leakage real-time warning result includes leakage location, leakage trend, and risk level.

3. The intelligent monitoring and early warning system for condensed water in HVAC system based on the Internet of Things according to claim 1 is characterized in that: The spectrum sensing scheduling module includes: The signal parameter calculation submodule calculates the signal interference correction index based on the signal strength value, signal-to-noise ratio value, and interference index value of the HVAC pipe sensor using the formula: ； Normalize the HVAC pipe sensor data to obtain normalized signal parameter values; in, represents the signal interference correction index, Represents the signal strength value, represents the signal-to-noise ratio value, represents the interference index value, represents the interference threshold; The spectrum density extraction submodule calculates the spectrum density of the condensate monitoring node based on the normalized signal parameter value, identifies the distribution of the spectrum density through the integral operation of the signal power, and obtains the spectrum density value of the condensate monitoring node; The frequency band screening and scheduling submodule calls the spectrum density value of the condensate monitoring node, screens the available frequency bands of the HVAC data gateway, analyzes the spectrum occupancy rate and interference distribution adaptability, and generates a spectrum scheduling allocation value.

4. The intelligent monitoring and early warning system for condensed water in HVAC system based on the Internet of Things according to claim 2 is characterized in that: The data transmission optimization module includes: The data extraction submodule extracts data from the HVAC data gateway based on the spectrum scheduling allocation value, filters the condensate monitoring related data, analyzes the data type and transmission rate, and establishes a condensate monitoring data set; The transmission priority calculation submodule calls the condensate monitoring data set, analyzes the criticality and delay sensitivity of the data, sets the data delay threshold, and uses the formula: ； Calculate the condensate water data transmission priority value; in, Represents the condensate data transmission priority value, Represents the data refresh rate, Represents the delay sensitivity of the current data, represents the delay sensitivity threshold, Represents the queuing time of data in the queue, Represents the length of the data packet; The transmission timing adjustment submodule calls the condensed water data transmission priority value, adjusts the transmission timing of the HVAC data gateway, optimizes the data queue order according to the priority, and generates a condensed water data transmission parameter set.

5. The intelligent monitoring and early warning system for condensed water in HVAC system based on the Internet of Things according to claim 3 is characterized in that: The vibration pressure monitoring module comprises: The signal acquisition submodule calls the condensate data transmission parameter set, extracts the vibration signal of the pipeline vibration sensor and the pressure signal of the condensate pressure sensor, analyzes the vibration amplitude, vibration frequency and pressure change rate, and obtains the vibration pressure signal set; The vibration and pressure calculation submodule sets the vibration offset reference based on the vibration pressure signal set, using the formula: ； The vibration offset value is calculated and combined with the pipeline condensate pressure signal to analyze the fluctuation situation, and the pressure change rate is compared with the pressure stability threshold to obtain the pressure fluctuation index; in, Represents the vibration offset value, represents the amplitude of the vibration signal, represents the measured vibration signal frequency, represents the vibration reference frequency, Represents the time duration value of the vibration signal, Representative The noise interference amount of the interfering data points, is the total number of interference data points; The condenser pressure state identification submodule calls the vibration offset value and the pressure fluctuation index, analyzes the pipeline vibration characteristics and the pressure distribution pattern, determines the condenser pressure state, matches the abnormal vibration and abnormal pressure fluctuation relationship, and obtains the condenser pressure state parameters.

6. The intelligent monitoring and early warning system for condensed water in HVAC system based on the Internet of Things according to claim 4 is characterized in that: The gas composition analysis module comprises: The gas data acquisition submodule extracts the gas concentration value, humidity value and temperature value in the condenser based on the condenser pressure state parameter, analyzes the gas type and concentration change trend, and obtains the gas characteristic parameter set; The gas anomaly calculation submodule sets the normal leakage threshold based on the gas characteristic parameter set, analyzes the gas leakage mode in combination with the change characteristics of the differentiated gas, determines the correlation between gas concentration and humidity and temperature, and identifies the abnormal fluctuation trend, using the formula: ； Calculate and obtain the abnormal index of condenser gas; in, Represents the abnormal index of condenser gas. Represents the gas concentration value, Represents the humidity of the monitoring area. Represents the base humidity, Represents the current ambient temperature. represents the gas diffusion rate; The condenser gas monitoring submodule calls the condenser gas anomaly index, analyzes the abnormal gas concentration in the condensate water abnormal area, screens the gas abnormal fluctuation value, matches the gas type, and generates a gas monitoring parameter set.

7. The intelligent monitoring and early warning system for condensed water in HVAC system based on the Internet of Things according to claim 5 is characterized in that: The leakage warning module comprises: The leakage trend analysis submodule analyzes the leakage gas concentration change trend, analyzes the leakage diffusion rate, sets the leakage trend reference value, and obtains the leakage trend parameter set based on the gas monitoring parameter set; The leakage risk identification submodule sets the risk identification threshold based on the leakage trend parameter set, using the formula: ； Combined with the gas data of differentiated areas, the risk level of condensate leakage is analyzed and the leakage risk index is calculated; in, represents the leakage risk index, Represents the current gas concentration, represents the leakage reference concentration, represents the gas diffusion rate, represents the diffusion time interval, Represents the current ambient humidity. Represents the baseline humidity in the leak area, Represents the number of diffusion calculation steps; The intelligent early warning submodule calls the leakage risk index, analyzes the condensate leakage risk level, screens the risk exceeding limit value, matches the leakage trend characteristics, and generates a real-time early warning result for condensate leakage.

Images