A method and system for detecting abnormal thermal conductivity of circulating water in heating equipment

Abstract

The application relates to a circulating water heat conduction capacity anomaly detection method and system of a heating device, and relates to the field of heating devices.The method comprises the following steps: acquiring a real-time room temperature sequence reported by a room temperature monitoring device through Internet of Things; counting a room temperature rising slope sequence and a room temperature falling slope sequence corresponding to the real-time room temperature sequence; determining a room temperature rising rate, a room temperature falling rate, a room temperature rising rate standard score and a room temperature falling rate standard score; inputting the room temperature rising rate, the room temperature falling rate, the room temperature rising rate standard score, the room temperature falling rate standard score, the room temperature rising slope sequence and the room temperature falling slope sequence into a pre-trained Wide&Deep neural network model to obtain a circulating water heat conduction capacity detection result of a monitored heating device and a target adjustment power. The application can accurately evaluate the circulating water heat conduction capacity of the heating device.

Description

Technical Field

[0001] This application relates to the field of heating equipment, and in particular to a method and system for detecting abnormal heat conduction capacity of circulating water in heating equipment. Background Technology

[0002] Currently, circulating water plays a crucial role in heating equipment such as wall-hung boilers. The thermal conductivity of the circulating water affects how effectively the equipment transfers heat to the room. If the thermal conductivity of the circulating water is too low, it will be difficult to meet the heating needs of users.

[0003] Insufficient heat conduction capacity of circulating water in heating equipment often means insufficient circulating water volume or abnormal water flow. Insufficient circulating water volume will cause the outlet water temperature of the heating equipment to quickly reach the set temperature and stop working, resulting in more frequent start-ups and shutdowns of the heating equipment and affecting its service life.

[0004] Therefore, there is an urgent need for a method to detect abnormalities in the thermal conductivity of circulating water in heating equipment. Summary of the Invention

[0005] Therefore, it is necessary to provide a method and system for detecting abnormal thermal conductivity of circulating water in heating equipment to address the aforementioned technical problems.

[0006] Firstly, a method for detecting abnormal thermal conductivity of circulating water in a heating system is provided, the method being applied to a cloud-based central server, the method comprising:

[0007] Acquire real-time room temperature sequences reported by room temperature monitoring devices via the Internet of Things (IoT), and real-time power reported by heating devices via the IoT;

[0008] Statistically analyze the room temperature rise slope sequence and room temperature fall slope sequence corresponding to the real-time room temperature sequence;

[0009] Determine the rate of increase in room temperature, the rate of decrease in room temperature, the standard score of the rate of increase in room temperature, and the standard score of the rate of decrease in room temperature.

[0010] The room temperature rise rate, room temperature fall rate, standard score of room temperature rise rate, standard score of room temperature fall rate, real-time power, room temperature rise slope sequence, and room temperature fall slope sequence are input into a pre-trained Wide&Deep neural network model to obtain the detection results of the circulating water thermal conductivity of the heating equipment to be monitored.

[0011] As an optional implementation, the step of statistically analyzing the room temperature rise slope sequence and room temperature fall slope sequence corresponding to the real-time room temperature sequence includes:

[0012] Identify the room temperature peaks and troughs in the real-time room temperature sequence;

[0013] The room temperature rise slope from the room temperature trough to the next room temperature peak is statistically represented as the room temperature rise slope sequence.

[0014] The rate of decrease in room temperature from the peak to the next trough is statistically represented as the room temperature decrease rate sequence.

[0015] As an optional implementation, determining the rate of increase in room temperature, the rate of decrease in room temperature, the standard fraction of the rate of increase in room temperature, and the standard fraction of the rate of decrease in room temperature includes:

[0016] The mean slope of the room temperature rise rate sequence is determined as the room temperature rise rate;

[0017] The mean slope of the room temperature decrease slope sequence is determined as the room temperature decrease rate;

[0018] Calculate the standard score of the room temperature rise rate in the pre-stored sample population of room temperature rise rates, and use it as the standard score of the room temperature rise rate;

[0019] Calculate the standard score of the room temperature decrease rate in the pre-stored sample population of room temperature decrease rates, and use it as the standard score of the room temperature decrease rate.

[0020] As an optional implementation, the training method for the Wide&Deep neural network model includes:

[0021] For each user, obtain the historical room temperature sequence of the preset time period reported by the user's room temperature monitoring device and the historical power reported by the heating device in the same time period;

[0022] Statistically analyze the historical room temperature rise slope sequence and the historical room temperature fall slope sequence corresponding to the historical room temperature sequence;

[0023] Based on the historical room temperature rise slope sequence and the historical room temperature fall slope sequence, determine the historical room temperature rise rate, the historical room temperature fall rate, the standard score of the historical room temperature rise rate, and the standard score of the historical room temperature fall rate.

[0024] The evaluation result of the user's heating equipment's circulating water thermal conductivity is determined based on the historical room temperature rise rate standard score, the historical room temperature fall rate standard score, the preset first standard score threshold, and the preset second standard score threshold.

[0025] The historical room temperature rise rate, the historical room temperature fall rate, the historical room temperature rise rate standard score, the historical room temperature fall rate standard score, and the historical power are concatenated and placed into the Wide part of the Wide&Deep neural network model;

[0026] The historical room temperature rise slope sequence and the historical room temperature fall slope sequence are concatenated and placed into the Deep part of the Wide&Deep neural network model;

[0027] The evaluation result of the circulating water's thermal conductivity is used as the user's training data label;

[0028] After training is complete, save the Wide&Deep neural network model and deploy it to the cloud.

[0029] As an optional implementation, the step of statistically analyzing the historical room temperature rise slope sequence and the historical room temperature fall slope sequence corresponding to the historical room temperature sequence includes:

[0030] Identify the room temperature peaks and troughs in the historical room temperature sequence;

[0031] The rate of increase in room temperature from the trough to the next peak is statistically analyzed as the historical rate of increase in room temperature.

[0032] The rate of decrease in room temperature from the peak to the next trough is statistically analyzed to form the historical rate of decrease in room temperature sequence.

[0033] As an optional implementation, determining the historical room temperature rise rate, historical room temperature fall rate, standard score of the historical room temperature rise rate, and standard score of the historical room temperature fall rate based on the historical room temperature rise slope sequence and the historical room temperature fall slope sequence includes:

[0034] The average slope of the historical room temperature rise rate sequence is determined as the historical room temperature rise rate.

[0035] The average slope of the historical room temperature decrease slope sequence is determined as the historical room temperature decrease rate;

[0036] Calculate the standard score of the historical room temperature rise rate in the pre-stored sample population of room temperature rise rates, and use it as the standard score of the historical room temperature rise rate;

[0037] Calculate the standard score of the historical room temperature decrease rate in the pre-stored sample population of room temperature decrease rates, and use it as the standard score of the historical room temperature decrease rate.

[0038] As an optional implementation, determining the evaluation result of the circulating water thermal conductivity of the user's heating equipment based on the historical room temperature rise rate standard score, the historical room temperature fall rate standard score, a preset first standard score threshold, and a preset second standard score threshold includes:

[0039] If the historical room temperature rise rate standard score is greater than the first standard score threshold, it is determined that the user's heating equipment has insufficient circulating water under the historical power.

[0040] If the historical room temperature drop rate standard score is greater than the second standard score threshold, it is determined that the heating water heat dissipation rate of the user's heating equipment is insufficient.

[0041] If the user's heating equipment has insufficient circulating water and / or insufficient heat dissipation rate, the assessment result of the user's heating equipment's circulating water thermal conductivity is abnormal; otherwise, it is normal.

[0042] As an optional implementation, the test results for the thermal conductivity of the circulating water include normal and abnormal values.

[0043] As an optional implementation, the method further includes:

[0044] When the circulating water thermal conductivity test result is abnormal, the target adjustment power is sent to the user so that the user can adjust the power of the heating equipment according to the target adjustment power.

[0045] In a second aspect, a detection system is provided, the system comprising a room temperature monitoring device, a heating device, and a cloud-based central server that applies the method as described in any one of the first aspects.

[0046] This application provides a method and system for detecting abnormalities in the thermal conductivity of circulating water in heating equipment. The technical solution provided by the embodiments of this application offers at least the following beneficial effects: acquiring real-time room temperature sequences reported by room temperature monitoring devices via the Internet of Things; statistically analyzing the room temperature rise slope sequence and room temperature fall slope sequence corresponding to the real-time room temperature sequences; determining the room temperature rise rate, room temperature fall rate, standard score of the room temperature rise rate, and standard score of the room temperature fall rate; inputting the room temperature rise rate, room temperature fall rate, standard score of the room temperature rise rate, standard score of the room temperature fall rate, the room temperature rise slope sequence, and the room temperature fall slope sequence into a pre-trained Wide&Deep neural network model to obtain the detection results of the thermal conductivity of the circulating water in the heating equipment to be monitored and the target adjustment power. This application utilizes real-time room temperature data to automatically statistically analyze the room temperature rise rate and fall rate, and combines this with a pre-trained Wide&Deep neural network model to accurately assess the thermal conductivity of the circulating water in the heating equipment. This avoids the errors and delays caused by manual diagnosis, enabling faster and more accurate detection of system problems. Furthermore, the embodiments of this application not only assess the room temperature change trend but also convert these trends into standard scores for comparison with historical sample populations. This statistically based assessment method can uncover more universal and representative patterns from the data, ensuring that abnormal equipment performance can be identified at an early stage.

[0047] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a schematic diagram of the structure of a detection system provided in an embodiment of this application;

[0050] Figure 2 A flowchart illustrating a method for detecting abnormal thermal conductivity of circulating water in a heating system, provided in an embodiment of this application;

[0051] Figure 3 A flowchart of another method for detecting abnormal thermal conductivity of circulating water in a heating device provided in an embodiment of this application;

[0052] Figure 4 A flowchart of another method for detecting abnormal thermal conductivity of circulating water in a heating device provided in an embodiment of this application;

[0053] Figure 5 A flowchart illustrating a training method for a Wide&Deep neural network model provided in an embodiment of this application;

[0054] Figure 6 A flowchart illustrating another training method for a Wide&Deep neural network model provided in this application embodiment;

[0055] Figure 7 A flowchart illustrating another training method for a Wide&Deep neural network model provided in this application embodiment;

[0056] Figure 8 A flowchart illustrating another training method for a Wide&Deep neural network model provided in this application embodiment. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0058] The method for detecting abnormal thermal conductivity of circulating water in heating equipment provided in this application embodiment can be applied to a cloud-based central server. For example... Figure 1 As shown, the heating device 110 can report its real-time power to the cloud central server 140 via the Internet of Things (IoT) 130, and the room temperature monitoring device 120 can report its real-time room temperature to the cloud central server 140 via the IoT 130. The cloud central server 140 is equipped with a pre-trained Wide&Deep neural network model, which can diagnose whether the heat conduction capacity of the circulating water is abnormal based on the real-time room temperature reported by the heating device 110, and provide a target adjustment power so that the user or the heating device 110 can adjust the power according to the target adjustment power.

[0059] The following will describe in detail, with reference to specific embodiments, a method for detecting abnormal thermal conductivity of circulating water in a heating equipment provided in this application. Figure 2 A flowchart illustrating an abnormal detection method for the thermal conductivity of circulating water in a heating system, provided in this application embodiment, is shown. The method is applied to a cloud-based central server. Figure 2 As shown, the specific steps are as follows:

[0060] Step 201: Obtain the real-time room temperature sequence reported by the room temperature monitoring device via the Internet of Things (IoT), and the real-time power reported by the heating device via the IoT.

[0061] In implementation, obtaining real-time room temperature sequences through room temperature monitoring devices is achieved using Internet of Things (IoT) technology. Each room temperature monitoring device periodically reports the indoor temperature to the server, forming time-series data. This real-time room temperature sequence reflects the trend of room temperature changes over time. For example, a residence may have multiple IoT temperature sensors installed, reporting the indoor temperature every 10 minutes. The central cloud server records 24 consecutive hours of room temperature data, forming a room temperature time series containing 144 data points. Heating equipment can stream and report real-time power according to preset reporting intervals.

[0062] Step 202: Calculate the room temperature rise slope sequence and room temperature fall slope sequence corresponding to the real-time room temperature sequence.

[0063] In practice, the acquired real-time room temperature sequence is statistically processed to calculate the slope of room temperature change. The slope reflects the rate of increase or decrease of room temperature within a specific time period. By calculating the ratio of the temperature change to the time interval in each time interval, the sequences of room temperature rise and fall slopes can be obtained, thus providing a more detailed characterization of the dynamic process of temperature change. For example, for the above 24-hour room temperature sequence, the slope of room temperature change every 10 minutes is statistically obtained. Assuming that the temperature rises from 20℃ to 22℃ in a certain period of time, and this period is 30 minutes, the corresponding room temperature rise slope is (22-20) / 30 = 0.067℃ / min.

[0064] As an optional implementation method, Figure 3 A flowchart of another method for detecting abnormal thermal conductivity of circulating water in a heating device provided in this application embodiment is shown below. Figure 3 As shown, the specific steps for calculating the room temperature rise slope sequence and room temperature fall slope sequence corresponding to the real-time room temperature sequence in step 202 are as follows:

[0065] Step 301: Identify the room temperature peaks and troughs in the real-time room temperature sequence.

[0066] In practice, a peak refers to the location where the room temperature reaches a local maximum at a given moment, while a trough refers to the location where the room temperature reaches a local minimum at a given moment. These peaks and troughs can be detected by processing the room temperature sequence using algorithms (such as sliding window or derivative methods). Assume the real-time room temperature sequence is: 22℃, 23℃, 24℃, 23.5℃, 23℃, and 22.5℃. In this sequence, 24℃ is a peak, and 22℃ is a trough. By analyzing these local extreme points, the fluctuation period of the room temperature can be identified.

[0067] Step 302: The room temperature rise slope from the room temperature trough to the next room temperature peak is statistically analyzed into a room temperature rise slope sequence.

[0068] In practice, after identifying the troughs and peaks, the slope of the temperature rise between each trough and the next peak is calculated to obtain a room temperature rise slope sequence. The specific calculation method is: Room temperature rise slope = (Peak temperature - Trough temperature) / (Time interval between peak and trough). This quantifies the rate of temperature rise for each step. Assuming a trough temperature of 22℃, a peak temperature of 24℃, and a time interval between trough and peak of 30 minutes, the corresponding room temperature rise slope is (24-22) / 30 = 0.067℃ / min. This result will be recorded in the room temperature rise slope sequence.

[0069] Step 303: The room temperature decrease slope from the room temperature peak to the next room temperature trough is statistically analyzed into a room temperature decrease slope sequence.

[0070] In practice, similar to the room temperature rise slope sequence, the slope of the temperature decrease process between each peak and the next trough is calculated to obtain the room temperature decrease slope sequence. The specific calculation method is: Room temperature decrease slope = (Room temperature at the trough - Room temperature at the peak) / (Time interval between the peak and the trough), to quantify the rate of temperature decrease at each step. Assuming the room temperature at the peak is 24℃, the room temperature at the trough is 22.5℃, and the time interval between the peak and the trough is 20 minutes, then the corresponding room temperature decrease slope is (22.5-24) / 20 = -0.075℃ / min. This result will be recorded in the room temperature decrease slope sequence.

[0071] Step 203: Determine the rate of increase in room temperature, the rate of decrease in room temperature, the standard score of the rate of increase in room temperature, and the standard score of the rate of decrease in room temperature.

[0072] In practice, to quantify the characteristics of room temperature changes, in addition to calculating the rates of increase and decrease in room temperature, it is also necessary to calculate their standardized scores (z-scores). This involves comparing each slope with the overall mean, and the standardized scores facilitate comparisons across different datasets. By calculating the standardized score for each data point, the degree of deviation from the overall temperature change trend can be determined.

[0073] As an optional implementation method, Figure 4 A flowchart illustrating another method for detecting abnormal thermal conductivity of circulating water in a heating system provided in this application embodiment is shown below. Figure 4 As shown, the specific steps for determining the rate of increase in room temperature, the rate of decrease in room temperature, the standard fraction of the rate of increase in room temperature, and the standard fraction of the rate of decrease in room temperature in step 203 are as follows:

[0074] Step 401: Determine the mean slope of the room temperature rise rate sequence as the room temperature rise rate.

[0075] In practice, the room temperature rise rate is determined by calculating the mean of the room temperature rise slope sequence. This sequence contains slopes between multiple troughs and peaks; averaging these slopes reflects the overall rate of room temperature increase over a period of time. This average value is the room temperature rise rate, representing the overall trend of room temperature increase within the monitoring period. In a 24-hour monitoring period, the collected room temperature rise slope sequence is [0.05, 0.06, 0.07]℃ / min. Calculating its mean yields a room temperature rise rate of (0.05 + 0.06 + 0.07) / 3 = 0.06℃ / min.

[0076] Step 402: Determine the mean slope of the room temperature decrease slope sequence as the room temperature decrease rate.

[0077] In practice, the room temperature decrease rate is determined by calculating the mean of the room temperature decrease slope sequence. The decrease slope sequence includes the slopes between multiple peaks and troughs. By calculating its average, the overall rate of room temperature decrease over a period of time can be obtained. This mean is the room temperature decrease rate, used to represent the overall trend of room temperature decrease. Within the same 24-hour monitoring period, the collected room temperature decrease slope sequence is [-0.04, -0.05, -0.06]℃ / min. By calculating its mean, the room temperature decrease rate is (-0.04 ± 0.05 ± 0.06) / 3 = -0.05℃ / min.

[0078] Step 403: Calculate the standard score of the room temperature rise rate in the pre-stored sample population of room temperature rise rates, and use it as the standard score of the room temperature rise rate.

[0079] In practice, to compare the currently calculated rate of room temperature rise with historical data, a standard score (z-score) needs to be calculated. The standard score determines the relative position of the current rate of room temperature rise by comparing it with the mean and standard deviation of a pre-stored historical sample population. The specific formula is: (Current rate of rise - Historical mean) / Standard deviation. This score reflects the relative extreme degree of the current rate of rise within the historical data. Assuming the mean of the pre-stored sample population of room temperature rise rates is 0.05℃ / min and the standard deviation is 0.01℃ / min, if the calculated rate of room temperature rise in the current monitoring period is 0.06℃ / min, then the standard score is (0.06 - 0.05) / 0.01 = 1. This means that the current rate of room temperature rise is one standard deviation higher than the historical average.

[0080] Step 404: Calculate the standard score of the room temperature decrease rate in the pre-stored sample population of room temperature decrease rates, and use it as the standard score of the room temperature decrease rate.

[0081] In practice, similar to the standard score for the rate of increase in room temperature, the standard score for the rate of decrease in room temperature is calculated by comparing the current rate of decrease with a pre-stored historical sample population. The formula for the standard score is: (Current rate of decrease - Historical mean) / Standard deviation. This helps determine whether the current rate of decrease in room temperature is abnormal or within the normal range. Assume the mean of the pre-stored sample population of room temperature decrease rates is -0.04℃ / min, and the standard deviation is 0.01℃ / min. If the calculated rate of decrease in room temperature during the current monitoring period is -0.05℃ / min, then the standard score is (-0.05 - (-0.04)) / 0.01 = -1. This indicates that the current rate of decrease in room temperature is one standard deviation below the historical average.

[0082] Step 204: Input the room temperature rise rate, room temperature fall rate, standard score of room temperature rise rate, standard score of room temperature fall rate, real-time power, room temperature rise slope sequence, and room temperature fall slope sequence into the pre-trained Wide&Deep neural network model to obtain the detection results of the circulating water thermal conductivity of the heating equipment to be monitored.

[0083] In implementation, the aforementioned room temperature rise rate, fall rate, their standard scores, real-time power, and slope sequence are input into a pre-trained Wide&Deep neural network model. This model combines the advantages of generalized linear models and deep neural networks, enabling it to simultaneously capture linear and complex nonlinear relationships. Through training and inference, the model can predict the circulating water thermal conductivity and regulation power of heating equipment. The model's output can be used to adjust the operation of the heating system, ensuring stable room temperature and optimal energy efficiency. In actual operation, the model, by inputting this real-time data, outputs a "normal" reading for the circulating water thermal conductivity and can also output a suggested target regulation power.

[0084] As an optional implementation method, the test results for the thermal conductivity of circulating water include normal and abnormal values.

[0085] As an optional implementation, when the thermal conductivity of the circulating water is detected as abnormal, a target adjustment power is sent to the user so that the user can adjust the power of the heating equipment according to the target adjustment power.

[0086] During implementation, when the circulating water thermal conductivity test result is abnormal, it means that the thermal conductivity of the heating equipment is not within the normal range, which may indicate a system malfunction or low operating efficiency. To address this, the Wide&Deep neural network model can output an optimized target adjustment power and send it to the user. The target adjustment power is the optimal heating power predicted by the neural network model based on real-time room temperature changes and equipment status, aiming to ensure that the indoor temperature is maintained within the set range while improving energy efficiency. Users can adjust the power settings of the heating equipment according to the system's suggestions to restore or optimize the heating effect.

[0087] As an optional implementation method, Figure 5 A flowchart illustrating a training method for a Wide&Deep neural network model provided in this application embodiment is shown below. Figure 5 As shown, the specific steps are as follows:

[0088] Step 501: For each user, obtain the historical room temperature sequence of the preset time period reported by the user's room temperature monitoring device and the historical power reported by the heating device in the same time period.

[0089] In implementation, to train the Wide&Deep neural network model, it is first necessary to acquire users' historical data. Specifically, historical room temperature sequences over a certain period are obtained from users' room temperature monitoring devices, and historical power data for the corresponding period is obtained from heating equipment. By pairing these two sets of data, the model can be provided with the relationship between the heating system's operating performance and heating power. For example, a user's room temperature monitoring device reports temperature data hourly over the past 14 days, while the heating equipment records its operating power during the same time period. This yields a 14-day historical room temperature sequence and corresponding historical power data.

[0090] Step 502: Calculate the historical room temperature rise slope sequence and the historical room temperature fall slope sequence corresponding to the historical room temperature sequence.

[0091] In practice, after acquiring historical room temperature data, these room temperature sequences are processed to statistically determine the historical room temperature rise and fall slope sequences. This is similar to previous real-time monitoring, where the rate of increase and decrease in room temperature is determined by calculating the slope between each trough and peak, and between peaks and troughs.

[0092] As an optional implementation method, Figure 6 A flowchart of another training method for a Wide&Deep neural network model provided in this application embodiment is shown below. Figure 6 As shown, the specific steps for calculating the historical room temperature rise slope sequence and the historical room temperature fall slope sequence corresponding to the historical room temperature series in step 502 are as follows:

[0093] Step 601: Identify room temperature peaks and troughs in the historical room temperature sequence.

[0094] In practice, identifying temperature peaks and troughs in historical temperature sequences is primarily accomplished by analyzing the trends in temperature changes at different time points. Peaks represent the moments when the temperature reaches a local maximum, and troughs represent the moments when the temperature reaches a local minimum. Time series analysis methods, such as sliding window or derivative methods, can be used to detect these local extrema.

[0095] Step 602: The room temperature rise slope from the room temperature trough to the next room temperature peak is statistically analyzed into a historical room temperature rise slope sequence.

[0096] In practice, after identifying the troughs and peaks in historical room temperatures, the temperature change between each trough and the next peak is calculated as the rising slope. The specific formula is: Rising Slope = (Peak Temperature - Trough Temperature) / (Time Interval Between Peak and Trough). This slope sequence records the rate of temperature increase for subsequent analysis. For example, assuming a trough temperature of 20℃, a peak temperature of 22℃, and a time interval between trough and peak of 60 minutes, the room temperature rising slope is (22-20) / 60 = 0.033℃ / min. This rising slope will be recorded in the historical room temperature rising slope sequence.

[0097] Step 603: The rate of decrease in room temperature from the peak to the next trough is statistically analyzed to form a historical rate of decrease in room temperature.

[0098] In practice, similarly, the temperature change between each peak and the next trough is calculated as the descent slope. The specific formula is: Descent Slope = (Trough Temperature - Peak Temperature) / (Time Interval Between Peak and Trough). This slope sequence records the rate of temperature decrease, used to assess the thermal conductivity of heating equipment. Assuming a peak temperature of 22℃, a trough temperature of 20.5℃, and a time interval between peaks and troughs of 40 minutes, the room temperature descent slope is (20.5 - 22) / 40 = -0.038℃ / min. This descent slope will be recorded in the historical room temperature descent slope sequence.

[0099] Step 503: Based on the historical room temperature rise slope sequence and the historical room temperature fall slope sequence, determine the historical room temperature rise rate, the historical room temperature fall rate, the standard score of the historical room temperature rise rate, and the standard score of the historical room temperature fall rate.

[0100] In implementation, based on the slope sequence obtained in step 502, the average values ​​of the historical room temperature rise and fall rates are calculated, and further standardized using a standard score. The standard score is used to assess the degree of deviation of the current user's heating effect relative to the overall trend, helping to reveal whether any anomalies exist. The average historical room temperature rise slope is 0.06℃ / min, with a standard deviation of 0.01℃ / min. Using the standard score formula, the calculated historical room temperature rise rate standard score is 2, indicating that the user's room temperature is rising relatively quickly.

[0101] As an optional implementation method, Figure 7 A flowchart illustrating another training method for a Wide&Deep neural network model provided in this application embodiment is shown below. Figure 7 As shown, the specific steps in step 503 to determine the historical rate of increase, the historical rate of decrease, the standard score of the historical rate of increase, and the standard score of the historical rate of decrease based on the historical rate of increase and the historical rate of decrease are as follows:

[0102] Step 701: Determine the average slope of the historical room temperature rise rate as the historical room temperature rise rate.

[0103] In practice, the historical room temperature rise rate is determined by calculating the mean of a historical room temperature rise slope sequence. This slope sequence records the rate of increase from multiple troughs to peaks; averaging these slopes yields the overall upward trend over a period of time. This historical rise rate can then be used to assess the overall heating efficiency of the heating system. Assuming a user's historical room temperature rise slope sequence is [0.03, 0.04, 0.05]℃ / min, the mean slope is calculated as (0.03 + 0.04 + 0.05) / 3 = 0.04℃ / min. This 0.04℃ / min is the user's historical room temperature rise rate.

[0104] Step 702: Determine the average slope of the historical room temperature decrease slope sequence as the historical room temperature decrease rate.

[0105] In practice, the historical room temperature decrease rate is determined by calculating the mean of a historical room temperature decrease slope sequence. This slope sequence records the rate of temperature decrease from peak to trough; averaging these slopes reflects the equipment's cooling efficiency or heat dissipation. Assuming the historical room temperature decrease slope sequence is [-0.02, -0.03, -0.04]℃ / min, its mean slope is calculated as (-0.02 + -0.03 + -0.04) / 3 = -0.03℃ / min. This -0.03℃ / min is the historical room temperature decrease rate.

[0106] Step 703: Calculate the standard score of the historical room temperature rise rate in the pre-stored sample population of room temperature rise rates, and use it as the standard score of the historical room temperature rise rate.

[0107] In implementation, to further determine whether the historical room temperature rise rate is normal, it is necessary to calculate its standard score within a pre-stored sample population. The standard score determines its relative position within the sample by comparing the historical rise rate with the sample population mean and standard deviation. The formula is: (Historical rise rate - Sample population mean) / Sample population standard deviation. This score is used to determine whether the current equipment's heating efficiency meets expectations. Assuming the sample population's historical room temperature rise rate means 0.035℃ / min and the standard deviation is 0.01℃ / min, if the current user's historical rise rate is 0.04℃ / min, then its standard score is (0.04 - 0.035) / 0.01 = 0.5. This indicates that the user's rise rate is slightly higher than the overall sample mean.

[0108] Step 704: Calculate the standard score of the historical room temperature decrease rate in the pre-stored sample population of room temperature decrease rates, and use it as the standard score of the historical room temperature decrease rate.

[0109] In practice, the standard score for the historical room temperature decrease rate is calculated in a similar manner, comparing the historical decrease rate with the mean and standard deviation of the overall sample. This standard score is used to assess the difference in heat dissipation performance of the heating equipment compared to the overall sample. Assuming the mean historical room temperature decrease rate of the overall sample is -0.03℃ / min and the standard deviation is 0.01℃ / min, if the current user's historical decrease rate is -0.04℃ / min, then its standard score is (-0.04 - (-0.03)) / 0.01 = -1. This indicates that the user's decrease rate is lower than the overall sample, and the heat dissipation rate is faster.

[0110] Step 504: Determine the evaluation result of the circulating water thermal conductivity of the user's heating equipment based on the historical room temperature rise rate standard score, the historical room temperature fall rate standard score, the preset first standard score threshold, and the preset second standard score threshold.

[0111] In implementation, the calculated historical room temperature rise rate standard score and fall rate standard score are compared with preset first and second standard score thresholds. If a user's standard score exceeds or falls below these thresholds, the system assesses the user's heating equipment as having abnormal circulating water thermal conductivity; otherwise, it is considered normal. The preset first standard score threshold is 1.5, and the second standard score threshold is -1.5. If a user's historical room temperature rise rate standard score is 2, exceeding the first standard score threshold, the circulating water thermal conductivity of their heating equipment is assessed as "too high," requiring attention to the equipment's energy efficiency.

[0112] As an optional implementation method, Figure 8 A flowchart illustrating another training method for a Wide&Deep neural network model provided in this application embodiment is shown below. Figure 8 As shown, the specific steps in step 504 to determine the evaluation result of the circulating water thermal conductivity of the user's heating equipment based on the historical room temperature rise rate standard score, the historical room temperature fall rate standard score, the preset first standard score threshold, and the preset second standard score threshold are as follows:

[0113] Step 801: If the historical room temperature rise rate standard score is greater than the first standard score threshold, it is determined that the user's heating equipment has insufficient circulating water under historical power conditions.

[0114] In implementation, when a user's historical room temperature rise rate standard score exceeds a preset first standard score threshold, it means that the heating equipment is experiencing an excessively rapid temperature rise at its historical power level. This typically indicates insufficient circulating water flow, failing to adequately absorb and transfer the generated heat, leading to a rapid increase in room temperature. Therefore, in this case, it can be determined that the user's heating equipment has an insufficient circulating water problem. Assuming the first standard score threshold is 3, if a user's historical room temperature rise rate standard score is 3.5, it indicates that the user's room temperature is rising rapidly. This may be due to insufficient circulating water flow in the heating system, failing to effectively disperse the generated heat, thus causing an excessively rapid temperature rise. Therefore, the system determines that the user's heating equipment has an insufficient circulating water problem.

[0115] Step 802: If the historical room temperature drop rate standard score is greater than the second standard score threshold, it is determined that the heating water heat dissipation rate of the user's heating equipment is insufficient.

[0116] In implementation, if a user's historical room temperature drop rate standard score exceeds a preset second standard score threshold, it indicates that the heating equipment's temperature is dropping slowly, meaning the heat dissipation rate of the heating water is insufficient. Insufficient heat dissipation rate may be due to inefficient heat dissipation components (such as radiators) or factors in the system that hinder heat dissipation. Assuming the second standard score threshold is 3.0, if a user's historical room temperature drop rate standard score is 3.2, it indicates that the user's heating water is cooling slowly. This may be due to inefficient radiators in the heating system, preventing heat from being dissipated in a timely manner. Therefore, the system determines that the user's heating equipment has a problem with insufficient heat dissipation rate of the heating water.

[0117] Step 803: If the user's heating equipment has insufficient circulating water and / or insufficient heat dissipation rate, the assessment result of the user's heating equipment's circulating water thermal conductivity is abnormal; otherwise, it is normal.

[0118] During implementation, if insufficient circulating water and / or insufficient heat dissipation rate are detected in a user's heating equipment, the system assesses that the user's circulating water thermal conductivity is abnormal. Conversely, if both indicators are within the normal range, the equipment's thermal conductivity is considered normal. For example, a user's historical room temperature rise rate standard score is 2.0 (insufficient circulating water) and the fall rate standard score is 0.8 (normal heat dissipation rate), therefore the system determines that the user's circulating water thermal conductivity is abnormal. If both are below the set threshold, the user's thermal conductivity assessment result is normal.

[0119] Step 505: Concatenate the historical room temperature rise rate, historical room temperature fall rate, historical room temperature rise rate standard score, historical room temperature fall rate standard score, and historical power, and place them into the Wide part of the Wide&Deep neural network model.

[0120] In implementation, the user's historical room temperature rise rate, fall rate, and corresponding standard scores are concatenated with historical power as input to the Wide part of the Wide&Deep neural network model. The Wide part processes linear features and is suitable for factors that directly affect heating efficiency. The user's historical room temperature rise rate (0.06℃ / min), fall rate (-0.05℃ / min), standard scores (2 and -1), and historical heating power within the corresponding time period are concatenated to form the input data for the Wide part.

[0121] Step 506: Concatenate the historical room temperature rise slope sequence and the historical room temperature fall slope sequence and place them into the Deep part of the Wide&Deep neural network model.

[0122] In implementation, historical room temperature rise and fall slope sequences are concatenated as input to the Deep part. The Deep part processes non-linear features, suitable for capturing complex time series changes and the dynamics of heating system operation. The user's room temperature rise slope sequence (e.g., [0.05, 0.06, 0.07]) and fall slope sequence (e.g., [-0.04, -0.05, -0.06]) over the past 30 days are concatenated as input data for the Deep part, used to train the model to capture complex patterns of room temperature changes.

[0123] Step 507: Determine the evaluation result of the circulating water's thermal conductivity as the user's training data label.

[0124] In implementation, the thermal conductivity assessment results of each user's heating system's circulating water will serve as labels for the training data. These labels allow the model to learn the relationship between room temperature variation characteristics and thermal conductivity, thus providing a foundation for future inferences. The user's thermal conductivity assessment results are categorized as "normal" or "abnormal," and these results are paired with corresponding input features to train the model.

[0125] Step 508: After training is complete, save the Wide&Deep neural network model and deploy it to the cloud.

[0126] In implementation, after training, the Wide&Deep neural network model is saved and deployed to the cloud for practical application. The cloud-based model can make inferences in real time based on new user data and continuously update to improve prediction accuracy. After training, the model is deployed to the cloud, and the heating system can access the model through the cloud to perform real-time performance evaluations and provide optimization adjustment suggestions for heating equipment for different users.

[0127] This application provides a method for detecting abnormalities in the thermal conductivity of circulating water in heating equipment. The method is applied to a cloud-based central server and includes: acquiring real-time room temperature sequences reported by room temperature monitoring devices via the Internet of Things; statistically analyzing the room temperature rise and fall slope sequences corresponding to the real-time room temperature sequences; determining the room temperature rise rate, room temperature fall rate, standard score of the room temperature rise rate, and standard score of the room temperature fall rate; and inputting these sequences into a pre-trained Wide&Deep neural network model to obtain the detection results of the circulating water thermal conductivity of the heating equipment under monitoring and the target adjustment power. This application utilizes real-time room temperature data to automatically calculate the room temperature rise and fall rates, and combines this with a pre-trained Wide&Deep neural network model to accurately assess the thermal conductivity of the circulating water in heating equipment. This avoids the errors and delays caused by manual diagnosis, enabling faster and more accurate detection of system problems. Furthermore, this application not only assesses room temperature change trends but also converts these trends into standard scores for comparison with historical samples. This statistically based assessment method can uncover more universal and representative patterns from the data, ensuring that abnormal equipment performance can be identified at an early stage.

[0128] It should be understood that, although Figures 2 to 8 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figures 2 to 8 At least some of the steps in the process may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0129] It is understood that the same / similar parts between the various embodiments of the methods described above in this specification can be referred to each other. Each embodiment focuses on the differences from other embodiments, and relevant parts can be referred to the description of other method embodiments.

[0130] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0131] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0132] It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0133] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0134] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0135] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method of detecting abnormality of heat transfer capacity of circulating water of a heating device, characterized by, The method is applied to a cloud central server, and the method comprises: obtaining a real-time room temperature sequence reported by a room temperature monitoring device through an Internet of Things and a real-time power reported by a heating device through the Internet of Things; statistically obtaining a room temperature rising slope sequence and a room temperature falling slope sequence corresponding to the real-time room temperature sequence; determining a room temperature rising rate, a room temperature falling rate, a room temperature rising rate standard score and a room temperature falling rate standard score; inputting the room temperature rising rate, the room temperature falling rate, the room temperature rising rate standard score, the room temperature falling rate standard score, the real-time power, the room temperature rising slope sequence and the room temperature falling slope sequence into a pre-trained Wide & Deep neural network model to obtain a circulating water heat conduction capacity detection result of a heating device to be monitored; the statistical obtaining of the room temperature rising slope sequence and the room temperature falling slope sequence corresponding to the real-time room temperature sequence comprises: identifying room temperature peaks and room temperature troughs in the real-time room temperature sequence; statistically obtaining a room temperature rising slope from the room temperature trough to the next room temperature peak as the room temperature rising slope sequence; statistically obtaining a room temperature falling slope from the room temperature peak to the next room temperature trough as the room temperature falling slope sequence; the determination of the room temperature rising rate, the room temperature falling rate, the room temperature rising rate standard score and the room temperature falling rate standard score comprises: determining a slope mean value of the room temperature rising slope sequence as the room temperature rising rate; determining a slope mean value of the room temperature falling slope sequence as the room temperature falling rate; calculating a standard score of the room temperature rising rate in a pre-stored room temperature rising rate sample population as the room temperature rising rate standard score; calculating a standard score of the room temperature falling rate in a pre-stored room temperature falling rate sample population as the room temperature falling rate standard score; the method further comprises: when the circulating water heat conduction capacity detection result is abnormal, sending a target adjustment power to a user so that the user adjusts the power of the heating device according to the target adjustment power.

2. The method of claim 1, wherein, a training method of the Wide & Deep neural network model, comprising: for each user, obtaining a historical room temperature sequence of a preset time period reported by a room temperature monitoring device of the user and a historical power reported by a heating device of the user in the same time period; statistically obtaining a historical room temperature rising slope sequence and a historical room temperature falling slope sequence corresponding to the historical room temperature sequence; based on the historical room temperature rising slope sequence and the historical room temperature falling slope sequence, determining a historical room temperature rising rate, a historical room temperature falling rate, a historical room temperature rising rate standard score and a historical room temperature falling rate standard score; determining a circulating water heat conduction capacity evaluation result of the heating device of the user according to the historical room temperature rising rate standard score, the historical room temperature falling rate standard score, a preset first standard score threshold and a preset second standard score threshold; performing field splicing on the historical room temperature rising rate, the historical room temperature falling rate, the historical room temperature rising rate standard score, the historical room temperature falling rate standard score and the historical power, and placing them into a Wide part of the Wide & Deep neural network model. concatenate the historical room temperature rising slope sequence and the historical room temperature falling slope sequence in a field, and put them into the Deep part of the Wide & Deep neural network model; determine the circulating water heat conduction capacity evaluation result of the user as the training data label; after the training is completed, save the Wide & Deep neural network model and deploy it to the cloud.

3. The method of claim 2, wherein, the statistics of the historical room temperature rising slope sequence and the historical room temperature falling slope sequence corresponding to the historical room temperature sequence include: identify the room temperature peaks and valleys in the historical room temperature sequence; statistical the room temperature rising slope from the room temperature valley to the next room temperature peak as the historical room temperature rising slope sequence; statistical the room temperature falling slope from the room temperature peak to the next room temperature valley as the historical room temperature falling slope sequence.

4. The method of claim 2, wherein, determine the historical room temperature rising rate, the historical room temperature falling rate, the historical room temperature rising rate standard score and the historical room temperature falling rate standard score based on the historical room temperature rising slope sequence and the historical room temperature falling slope sequence, including: determine the average slope of the historical room temperature rising slope sequence as the historical room temperature rising rate; determine the average slope of the historical room temperature falling slope sequence as the historical room temperature falling rate; calculate the standard score of the historical room temperature rising rate in the pre-stored room temperature rising rate sample population as the historical room temperature rising rate standard score; calculate the standard score of the historical room temperature falling rate in the pre-stored room temperature falling rate sample population as the historical room temperature falling rate standard score.

5. The method of claim 2, wherein, determine the circulating water heat conduction capacity evaluation result of the user's heating equipment according to the historical room temperature rising rate standard score, the historical room temperature falling rate standard score, the pre-set first standard score threshold and the pre-set second standard score threshold, including: if the historical room temperature rising rate standard score is greater than the first standard score threshold, it is determined that the circulating water of the user's heating equipment is insufficient under the historical power; if the historical room temperature falling rate standard score is greater than the second standard score threshold, it is determined that the heating water heat dissipation rate of the user's heating equipment is insufficient; if the circulating water of the user's heating equipment is insufficient and / or the heating water heat dissipation rate is insufficient, the circulating water heat conduction capacity evaluation result of the user's heating equipment is abnormal, otherwise it is normal.

6. The method of claim 1, wherein, the circulating water heat conduction capacity detection result includes normal and abnormal.

7. A detection system characterized by, the system includes a room temperature monitoring device, a heating equipment and a cloud central server applying the method of any one of claims 1-6.

Images