Operation data analysis processing method and system for heat supply pipe network

Abstract

The invention discloses an operation data analysis and processing method and system for a heat supply pipe network, and relates to the technical field of intelligent heat supply, and the method comprises the steps: determining the operation change conditions of monitoring data of the heat supply pipe network in different outdoor temperature intervals and different heat supply flow intervals, determining an abnormal fluctuation flow interval in the heat supply flow interval based on the operation change condition; when the adjustment change condition of the heat supply flow in the outdoor temperature interval meets the requirement, the heat supply deviation flow interval is calculated; and according to the coincidence condition of the heat supply deviation flow intervals in the abnormal fluctuation flow intervals of the different heat supply pipe networks and in combination with the distribution condition of the outdoor temperature intervals under the different weather types, the identification processing time periods of the operation data of the heat supply pipe networks under the different weather types are determined. According to the method, the heat preservation performance of the heat supply pipe network is analyzed, and the reliability degree of temperature monitoring processing of the heat supply pipe network is improved.

Description

Technical Field

[0001] This invention relates to the field of smart heating technology, and in particular to a method and system for analyzing and processing operational data of heating pipeline networks. Background Technology

[0002] With the acceleration of urbanization, centralized heating systems have become the main method of building heating in cold northern regions. As a crucial infrastructure connecting heat sources and end-users, the operating status of the heating network directly affects heating quality and energy efficiency. In recent years, with the continuous development of digital technology and information sensing equipment, outdoor temperature sensors, flow meters, pressure gauges, and other monitoring devices have been widely deployed in heating systems to achieve real-time monitoring of the heating network's operating status and generate a large amount of dynamic operating data. Existing heating analysis methods are mostly based on empirical formulas or statistical models, primarily focusing on the macroscopic coupling relationship between outdoor temperature and heating capacity, adjusting key parameters such as supply water temperature, return water temperature, or heating flow rate. However, these methods have limited adaptability to complex weather changes, regional differences in heat users, and the system's dynamic feedback capabilities, leading to increasingly prominent problems such as lagging control measures and difficulty in timely identification of network operation deviations. Therefore, how to conduct more refined and multi-dimensional analysis and processing of heating operation data to improve the intelligent adjustment capabilities of heating systems in various environmental scenarios has become a key focus of industry technological development.

[0003] Currently, some systems have attempted to introduce intelligent algorithms for predicting and diagnosing heating data, but they still mainly focus on single or a few operating parameters, without fully considering the correlation between heating flow fluctuations under varying outdoor temperature ranges. Furthermore, their ability to identify abnormal fluctuations is weak, and the causal relationship between heating deviations for individual users and changes in the overall network operation has not yet been established, making it difficult to support the formulation of precise heating control strategies. In addition, existing technologies mostly employ fixed analysis strategies, failing to differentiate heating network operation patterns based on weather type changes, and are ill-suited to unstable climatic conditions such as extreme temperatures and alternating periods of sunshine and snow. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method for analyzing and processing operational data of heating pipe networks to address the problems of insufficient identification of operational changes in heating flow rate under different outdoor temperature ranges and lack of correlation analysis between abnormal flow rate fluctuations and heating deviations of heat users in existing technologies.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for analyzing and processing operational data of a heating network, comprising: based on outdoor temperature monitoring data, determining the operational changes of the monitoring data of the heating network under different outdoor temperature ranges and different heating flow ranges, and determining the abnormal fluctuation flow range in the heating flow range based on the operational changes; Determine the historical adjustment data of heating flow rate within the outdoor temperature range. Based on the historical adjustment data of heating flow rate, calculate the heating deviation flow rate range when the adjustment and change of heating flow rate within the outdoor temperature range meets the requirements. Based on the historical operating data of abnormal flow ranges of different heating pipe networks within the outdoor temperature range and the heating deviation of heat users within the abnormal flow range, the heating deviation flow range within the abnormal flow range is determined. Based on the overlap of heating deviation flow ranges within the abnormal fluctuation flow ranges of different heating networks, and combined with the distribution of outdoor temperature ranges under different weather types, the identification and processing time periods for the operating data of heating networks under different weather types are determined.

[0007] As a preferred embodiment of the operational data analysis and processing method for heating pipe networks described in this invention, the step of using outdoor temperature monitoring data as a basis includes collecting outdoor temperature time series data. Heating flow rate With each temperature measuring point , , Indicates the number of monitoring points; performs basic data cleaning and time alignment. Based on outdoor temperature monitoring data, different outdoor temperature ranges and heating flow ranges are divided. Several flow ranges ,in Indicates the traffic range index; A two-dimensional grid of temperature-flow rate is obtained, and statistics and deviation calculations are performed within the grid. By analyzing the deviation of different temperature measuring points in the monitoring data, the temperature deviation is dynamically monitored, the operation and changes of the monitoring data in the region are analyzed, and abnormal intervals with significant fluctuations in the operation and changes of the heating flow rate are identified and automatically marked as abnormal fluctuation flow rate intervals.

[0008] As a preferred embodiment of the operational data analysis and processing method for heating pipe networks described in this invention, the operational changes of the monitoring data under different heating flow ranges include dividing the outdoor temperature into several temperature ranges according to intervals. , Indicates a temperature range index; The historical heating flow range is divided into each block at equal intervals. Internally, summarize the data from each measuring point. Observe the temperature and take a robust statistic as the representative value of the current block; For the same flow range By comparing the range of representative values ​​at different temperature ranges, the temperature deviation of the measuring point within the flow rate range is obtained. ; Will The measuring points are marked as variable temperature measuring points; This indicates the temperature threshold that fluctuates across temperature ranges at the measuring point; it also counts the percentage of measuring points that change within the current flow range. ,by This reflects the operational changes within the current traffic range.

[0009] As a preferred embodiment of the operation data analysis and processing method for heating pipe networks described in this invention, the abnormal fluctuation flow range includes: determining the heating deviation flow range within the abnormal fluctuation flow range based on historical operation data of different heating pipe networks within the outdoor temperature range and the heating deviation of heat users within the abnormal fluctuation flow range. For each flow range If the proportion of measuring points changes Then the current traffic range will be marked as an abnormally fluctuating traffic range, and ; Obtain the anomaly set ; This indicates the safety threshold for abnormal fluctuations.

[0010] As a preferred embodiment of the operational data analysis and processing method for heating pipe networks described in this invention, the heating deviation flow range includes, in each block Internally, it identifies historical regulation events, records the flow rate before and after each regulation, and calculates the regulation amount; the ratio of the regulation amount to the pre-regulation flow rate is greater than... Events are marked as adjustments that do not meet the requirements, and the percentage of adjustment events that do not meet the requirements within a block is calculated. ; This represents the abnormal adjustment threshold, obtained from historical operating data; Using the proportion of operational changes and adjustments not meeting requirements as input features , ; Generate continuous scores for machine learning evaluation using a trained model. ;in accordance with Adjustment threshold for the determination block ,like If the requirements are met, the heating deviation flow range shall be determined when the adjustment and variation of the heating flow rate within the outdoor temperature range meets the requirements. The heating deviation of heat users is determined based on the deviation between the heating supply and the target heating supply within the abnormal fluctuation flow range; an LSTM model optimized based on the GWO algorithm is used to determine whether the adjustment and variation of the heating flow within the outdoor temperature range meets the requirements. The method for determining the heating deviation flow range within the abnormal fluctuation flow range is as follows: Based on the heating deviation of heat users within the abnormal flow fluctuation range, determine the deviation between the heating supply of heat users and the target heating supply within the abnormal flow fluctuation range; heat users whose deviation does not meet the requirements are identified as heat users with heating deviation. The number of heat users with heating deviations is used to determine whether the abnormal fluctuation flow range is a heating deviation flow range.

[0011] As a preferred embodiment of the operational data analysis and processing method for heating pipe networks described in this invention, the distribution of outdoor temperature ranges under different weather types includes classifying the annual temperature according to... The step size is set to a set of target temperature points; the difference between the daily average outdoor temperature and the target point is less than... At that time, the current date will be assigned to the corresponding weather type. ; In each The following analysis summarizes the three types of indicators to derive a data analysis and processing strategy for the heating network operation, specifically including: Depend on The number of abnormal fluctuation flow intervals obtained from statistics is from The proportion of heating deviation flow ranges obtained from statistics is from The percentage of adjustments that do not meet the requirements is calculated by reverse calculation.

[0012] As a preferred embodiment of the method for analyzing and processing operational data of heating pipe networks according to the present invention, the step of determining the identification and processing period of operational data of the heating pipe network under different weather types includes situations where the abnormal flow fluctuation range of the heating pipe network highly overlaps with the heating deviation flow range, and the proportion of abnormal flow fluctuation ranges is higher than [a certain percentage]. If the insulation performance of the heating network is poor and the number of heat users with abnormal flow deviations is large within the abnormal flow range, then all weather types will fall within the abnormal flow range, and temperature measurement points will be identified and processed according to the preset time cycle.

[0013] Secondly, the present invention provides an operational data analysis and processing system for heating pipe networks, including a data acquisition and interval division module, which accesses and cleans outdoor temperature, heating flow rate, and measuring point temperature, divides outdoor temperature intervals, and divides flow rate intervals at equal intervals according to historical ranges. The abnormal fluctuation identification module is used to determine the abnormal fluctuation flow range, summarize the characteristics of the regulation events, and use a machine learning scoring function to evaluate whether the regulation meets the requirements. The heating deviation range identification module is used to combine the actual heating user's heat supply with the target heating supply, calculate the deviation ratio, and determine the heating deviation flow range. The weather type and strategy generation module summarizes the deviation ratio, adjusts non-compliant ratio indicators, and generates analysis and processing strategies for the operation data of the heating network under different weather types based on threshold rules.

[0014] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the method for analyzing and processing operating data of a heating network as described in the first aspect of the present invention.

[0015] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for analyzing and processing operating data of a heating network as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: By utilizing the operational changes in monitoring data of the heating pipeline network under different outdoor temperature ranges and different heating flow ranges, abnormal fluctuation flow ranges within the heating flow ranges are identified. This enables the analysis of the insulation performance of the heating pipeline network based on the changes in temperature monitoring data under different outdoor temperatures, and facilitates the screening of abnormal fluctuation flow ranges under different insulation performance conditions. It also lays the foundation for further determining the time periods for temperature measurement point identification based on these abnormal fluctuation flow ranges. By considering the overlap of heating deviation flow ranges within the abnormal fluctuation flow ranges of different heating pipeline networks, and combining this with the distribution of outdoor temperature ranges under different weather types, the analysis and processing strategies for the operating data of the heating pipeline network under different weather types are determined. This allows for the determination of the time periods for temperature measurement point identification based on the distribution of outdoor temperature ranges requiring temperature identification, the insulation performance of the heating pipeline network, and the heating deviations of heat users, thereby improving the reliability of temperature monitoring and processing of the heating pipeline network. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. 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.

[0018] Figure 1 This is a flowchart of a method for analyzing and processing operational data for heating pipe networks. Detailed Implementation

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0020] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0022] Reference Figure 1 This is one embodiment of the present invention, which provides a method for analyzing and processing operational data of a heating network, comprising the following steps: S1: Based on outdoor temperature monitoring data, determine the operational changes of the monitoring data of the heating network under different outdoor temperature ranges and different heating flow ranges, and determine the abnormal fluctuation flow range in the heating flow range based on the operational changes.

[0023] Furthermore, the collection of outdoor temperature monitoring data includes collecting outdoor temperature time series data. Heating flow rate With each temperature measuring point , , This indicates the number of monitoring points; basic data cleaning and time alignment are performed.

[0024] Based on outdoor temperature monitoring data, different outdoor temperature ranges and heating flow ranges are divided. Collect and align three types of time series data: outdoor temperature Heating flow rate Pipeline temperature measuring points ( Number the measurement points. (Total number of measurement points).

[0025] Only time alignment and necessary missing test completion are performed; no additional thresholds or hyperparameters are introduced.

[0026] Divide the outdoor temperature range into intervals: Divide into several intervals at equal intervals .

[0027] Furthermore, based on outdoor temperature monitoring data, the operational changes of the monitoring data of the heating network under different outdoor temperature ranges and different heating flow ranges are determined, and the abnormal fluctuation flow ranges in the heating flow ranges are determined based on the operational changes.

[0028] The outdoor temperature range is divided into equal intervals based on a 2-degree Celsius interval, and the heating flow range is divided into equal intervals based on the historical heating flow range of the heating network. For example, it can be divided into 5 or 10 intervals.

[0029] The operational changes in the monitoring data include the deviation of the monitored temperature at different temperature measuring points in the heating network within the heating flow range, and between different outdoor temperature ranges.

[0030] It is understood that determining the abnormal fluctuation range of the heating flow rate within the aforementioned operational changes specifically includes: Based on the aforementioned operational variations, the deviation of the monitored temperature at different temperature measurement points in the heating network within the heating flow range is determined between different outdoor temperature ranges.

[0031] Based on the deviation of the monitored temperature between different outdoor temperature ranges, the variable temperature measuring points among the temperature measuring points are determined.

[0032] By utilizing temperature fluctuation data from points within the heating network, it is determined whether the stated heating flow rate range constitutes an abnormally fluctuating flow rate range. The heating flow rate range is based on historical data. The range of values ​​is divided into equal intervals. (5 or 10 segments can be selected, and the segment number is recorded as follows) ). The outdoor temperature range is divided into indivual.

[0033] In each two-dimensional block Internal (index is) , For each measuring point Calculate the representative temperature of this block. The formula is expressed as: For each measuring point In a specific flow range and temperature range Inside, a representative temperature is calculated. This represents temperature data. In a specific traffic range and temperature range The median below.

[0034] Get across all temperature ranges The measuring point is in the same flow range The representative value set below .

[0035] Calculation of measurement point variation and measurement of measurement points In the traffic range The range of fluctuations (range) as outdoor temperature changes. The formula is expressed as: And based on this, determine the temperature measurement points. The threshold is used The formula is expressed as: in, This is an indicator function; it takes the value 1 if the condition is met, and 0 otherwise.

[0036] Several flow ranges The system obtains a two-dimensional grid of temperature-flow rate blocks, performs statistics and deviation calculations within the blocks, analyzes the deviation of different temperature measuring points in the monitoring data, dynamically monitors the temperature deviation, analyzes the thermal insulation performance of the area, identifies abnormal intervals with significant fluctuations in the heating flow rate range, and automatically marks them as abnormal fluctuation flow rate intervals.

[0037] It should be noted that when the maximum deviation of the monitored temperature between different outdoor temperature ranges within the heating flow range is greater than 2 degrees Celsius, the temperature measuring point is determined to be a fluctuating temperature measuring point. When the number of fluctuating temperature measuring points in the heating network is large, in one possible embodiment, when the number of fluctuating temperature measuring points accounts for more than 1 / 4 of the total number of temperature measuring points in the heating network, the heating flow range is determined to be an abnormal fluctuation flow range. The abnormal fluctuation flow range reflects the difference in the thermal insulation performance of the heating network. When an abnormal fluctuation flow range exists, it indicates that the thermal insulation performance of the heating network is poor.

[0038] S2: Determine the historical adjustment data of heating flow rate within the outdoor temperature range. Based on the historical adjustment data of heating flow rate, when the adjustment and change of heating flow rate within the outdoor temperature range meets the requirements, calculate the heating deviation flow rate range within the abnormal fluctuation flow rate range.

[0039] Furthermore, the operational changes in monitoring data under different heating flow ranges include dividing the outdoor temperature into several temperature ranges at intervals. The historical heating flow range is divided into equal intervals in each block. Internally, summarize the data from each measuring point. Observe the temperature and take a robust statistic as the representative value for the current block; for the same flow range By comparing the range of representative values ​​at different temperature ranges, the temperature deviation of the measuring point within the flow rate range is obtained. .

[0040] Will The measuring points are marked as variable temperature measuring points; This indicates the temperature threshold that fluctuates across temperature ranges at the measuring point; it also counts the percentage of measuring points that change within the current flow range. ,by This reflects the operational changes within the current traffic range.

[0041] Operational changes are summarized in each flow range. Within, the percentage of statistical change measurement points As an indicator of the intensity of operational changes within this range: in, The larger the value, the more measurement points that show significant temperature fluctuations with changes in outdoor temperature within that flow range, and the weaker the consistency of pipeline insulation and operational stability.

[0042] The output consists of three sets of values. Used to retain the representative temperature of each block; , Characterizes fluctuations at the measurement point level; Describe the overall changes in traffic flow at the interval level.

[0043] based on Identify the range of abnormal flow fluctuations and continue to conduct adjustment assessments.

[0044] Determine the historical adjustment data of the heating flow rate within the outdoor temperature range. Based on the historical adjustment data of the heating flow rate, determine whether the adjustment and change of the heating flow rate within the outdoor temperature range meets the requirements, and then proceed to the next step.

[0045] The historical adjustment data of heating flow within the outdoor temperature range includes the number of load adjustments and the adjustment amount of heating flow under different load adjustment numbers, that is, the change in heating flow before and after adjustment.

[0046] It is understood that, based on the historical adjustment data of the heating flow rate, the adjustment and variation of the heating flow rate within the outdoor temperature range are determined to meet the requirements, specifically including: Based on the historical adjustment data of the heating flow rate, the number of load adjustments of the heating network under different heating flow rate ranges within the outdoor temperature range is determined.

[0047] Enter outdoor temperature range Heating flow range Percentage of changes in measuring points Within the traffic range Inside, the temperature variation across different outdoor temperature ranges exceeded The proportion of measuring points.

[0048] Determine the abnormal flow range within each temperature-flow block. The next step is to assess whether the adjustment meets the requirements.

[0049] The determination of abnormal flow range is based on the percentage change in measuring points. For each flow range Single threshold The determination formula is as follows: when At that time, The range marked as abnormal flow fluctuation range (the range where insulation differences and operational instability are relatively significant).

[0050] Historical adjustment data extraction and adjustment do not meet the identification requirements in each block Within, the statistically moderating event set (total) (Next time). Regarding the first... The adjustment is denoted as: Use a 5% relative change threshold to identify events where the adjustment amount does not meet requirements: The percentage of non-compliance within the block is calculated using the formula: in, This indicates the adjusted heating flow rate; This indicates the heating flow rate before adjustment. This formula is used to determine the first... Does the adjustment fail to meet the requirements? This indicates the percentage of events within the block that do not meet the adjustment requirements.

[0051] The intuitive meaning is, The larger the value, the more likely the adjustment action is to result in excessive relative variation (>5%) under the given temperature-flow conditions.

[0052] Based on the adjustment amount of heating flow under different load adjustment times, determine the number of load adjustments where the adjustment amount does not meet the requirements.

[0053] Based on the number of load adjustments that do not meet the requirements in different heating flow ranges, and the number of load adjustments that do not meet the requirements in the outdoor temperature range, it is determined whether the adjustment changes in heating flow rate in the outdoor temperature range meet the requirements.

[0054] It is understood that when the ratio of the adjusted heating flow rate to the heating flow rate of the heating network before adjustment is greater than 5%, the number of load adjustments is determined to be the number of load adjustments where the adjustment amount does not meet the requirements.

[0055] Optionally, based on the composition data of the number of load adjustments that do not meet the requirements under different heating flow ranges and the number of load adjustments that do not meet the requirements in the heating network within the outdoor temperature range, it is determined whether the adjustment variation of the heating flow in the outdoor temperature range meets the requirements, and an LSTM model optimized based on the GWO algorithm is used for determination.

[0056] Forming the input feature vector: in, Representing an interval The adjustment ratio that does not meet the requirements.

[0057] Based on GWO-LSTM intelligent judgment of adjustment changes.

[0058] Data preprocessing was performed, including range standardization of historical heating network data to divide it into training and test sets; The range standardization formula is expressed as follows: Key features were extracted, including the number of load adjustments that did not meet requirements under different heating flow ranges, and the percentage of such load adjustments in the heating network within the outdoor temperature range.

[0059] Model parameter initialization, determining LSTM structure parameters: Number of input layer units (corresponding feature dimension) (correspond ).

[0060] Number of output layer units (binary classification) (output satisfaction level) ).

[0061] Number of hidden layer nodes (initially set to 10-30) Dropout retention rate GWO parameter: Number of wolves Maximum number of iterations .

[0062] Optimization range: learning rate Regularization coefficient .

[0063] The GWO optimization process includes encoding the location of each gray wolf. This represents a set of LSTM hyperparameters.

[0064] Construct a fitness function using cross-entropy loss plus a regularization term as the objective function: in, This is the output predicted by the LSTM.

[0065] Position update formula, gray wolf packs are divided into Optimal Second best The third category of superior quality is updated as follows: in, ,parameter , , Decrease linearly to 0. Indicates the first The "position vector" of Sekiro encodes a set of LSTM hyperparameters to be evaluated. This represents the fitness function value, i.e., the value in the hyperparameters. The sum of the cross-entropy loss and the regularization term of the model obtained from the training. Indicates in hyperparameters The output score is obtained by LSTM prediction (for the sample). ). This represents the set of weight parameters for the LSTM; its norm is incorporated into the regularization term to limit the model complexity. This represents the position vector of the three "alpha wolves" with the best, second best, and third best fitness in the GWO, and is used to guide the updates of the remaining individuals. This represents the GWO update coefficient vector, where Control the contraction / expansion and the search direction. Control the intensity of the encirclement of the optimal solution. The shrinkage factor of GWO decreases linearly to 0 with each iteration, and is used to transition from global search to local exploitation. Indicates that the element is taken from The random vectors are introduced to enhance search diversity. The distance vector from the current individual to the three alpha wolves is defined as follows: , used to calculate update steps. This indicates the candidate contraction positions with reference to the three-headed wolves. (And so on), used to calculate the weighted average of the new position.

[0066] Iterate until the fitness converges, then output the optimal parameters. .use Construct an LSTM network, using a sliding window mechanism to generate time series samples (window size 24-72 hours) during training, and enable early stopping (patience=10). Evaluate the model output using the LSTM network.

[0067] Introduce only dependencies and Scoring function Output interval-based scores : A binary conclusion is given regarding whether the adjustment meets the requirements, using a threshold of 0.5: Among them, when The temperature-flow rate regulation of this zone meets the requirements (more than half of the scores are met).

[0068] when The adjustment of this block does not meet the requirements (the score is less than half), and it needs to be given priority and optimized in subsequent steps.

[0069] Output and a minimal set of results for subsequent use, including a set of anomalous fluctuations. Adjustment evaluation matrix and corresponding ratings .

[0070] It should be noted that, it should be noted that, This reflects the differences in stability / insulation across temperature variations within the same flow range; This reflects the compliance of the adjustment actions themselves within the block; By combining the two, a unified standard of pass / fail is output. Within the anomaly set, user deviations will be combined to further identify heating deviation flow ranges; S4 will be based on... and The distribution of weather patterns is used to generate dynamic analysis and monitoring strategies based on weather type.

[0071] S3: Based on the historical operating data of the abnormal flow fluctuation range of different heating pipe networks within the outdoor temperature range and the heating deviation of heat users within the abnormal flow fluctuation range, determine the heating deviation flow range within the abnormal flow fluctuation range.

[0072] Furthermore, the abnormal flow fluctuation range includes the determination of the heating deviation flow range within the abnormal flow fluctuation range based on historical operating data of different heating pipe networks within the outdoor temperature range and the heating deviation of heat users within the abnormal flow fluctuation range.

[0073] For each flow range If the proportion of measuring points changes Then the current traffic range will be marked as an abnormally fluctuating traffic range, and ; Obtain the anomaly set ; This indicates the safety threshold for abnormal fluctuations.

[0074] Within the identified abnormal flow fluctuation range, the flow range of heating deviation is identified based on the deviation between the actual heating supply to heat users and the target heating supply, providing a precise target for subsequent strategies.

[0075] By flow range Aggregated historical operation segments; actual heat supply to each heat user within this interval. With target heat supply : ,in .

[0076] User-level deviation measurement and labeling, deviation measurement (uniform notation and caliber) for each abnormal interval With each user Calculate the relative deviation: in, This reflects the user's time in the interval The relative deviation of heating supply within the area is measured using absolute values ​​to uniformly determine whether it is too much or too little.

[0077] The formula for determining users with deviations (threshold 10%) is expressed as follows: in, Indicates user In the interval For users with heating deviations (deviations exceeding 10%).

[0078] Interval-level summarization and percentage calculation, in each abnormal interval Within, the percentage of hot users with statistical bias: in, Indicates the interval Within, the proportion of users with deviation heat relative to the total number of users.

[0079] The formulas for determining the heating deviation flow range and the output range (threshold is 0.3) are as follows: When the proportion of users with deviation heat is greater than 30%, this range will be... Marked as heating deviation flow range For each Output Summary Collection .

[0080] To quantify overlap, the overlap rate can be recorded, expressed by the formula: The identification of heating deviation flow ranges includes, in each block Internally, it identifies historical regulation events, records the flow rate before and after each regulation, and calculates the regulation amount; the ratio of the regulation amount to the pre-regulation flow rate is greater than... Events are marked as adjustments that do not meet the requirements, and the percentage of adjustment events that do not meet the requirements within a block is calculated. .

[0081] Using the proportion of operational changes and adjustments not meeting requirements as input features , ; Generate continuous scores for machine learning evaluation using a trained model. ;in accordance with Adjustment threshold for the determination block ,like If yes, it meets the requirements; otherwise, it does not.

[0082] The heating deviation of heat users is determined based on the deviation between the heat supply and the target heat supply within the abnormal flow fluctuation range.

[0083] Furthermore, the method for determining the heating deviation flow range within the abnormal fluctuation flow range is as follows: Based on the heating deviation of heat users within the abnormal flow fluctuation range, determine the deviation between the heating supply of heat users and the target heating supply within the abnormal flow fluctuation range; heat users whose deviation does not meet the requirements are identified as heat users with heating deviation.

[0084] The number of heat users with heating deviations is used to determine whether the abnormal fluctuation flow range is a heating deviation flow range.

[0085] When the overlap between the abnormal flow fluctuation range and the heating deviation flow range of the heating network is high and the number of abnormal flow fluctuation ranges is large, the heating network has poor insulation performance and there are many heating deviation users in the abnormal flow fluctuation range. Therefore, regardless of the weather type, temperature measurement points are identified and processed in all abnormal flow fluctuation ranges according to a preset time period.

[0086] In one possible embodiment, when the number of abnormal flow fluctuation intervals is more than four and the overlap rate between the abnormal flow fluctuation intervals and the heating deviation flow intervals is greater than one-third, it is determined that the abnormal flow fluctuation intervals and the heating deviation flow intervals of the heating network have a high degree of overlap and a large number of abnormal flow fluctuation intervals.

[0087] When the number of abnormal flow fluctuation ranges is small, it indicates that the heat preservation effect is good. Therefore, regardless of the weather type, temperature measurement points are identified and processed according to the preset time cycle in all outdoor temperature ranges where the adjustment and change of heating flow do not meet the requirements.

[0088] It should be noted that when there are many abnormal flow fluctuation ranges, but the overlap between the abnormal flow fluctuation ranges and the heating deviation flow ranges in the heating network is not high, it indicates that the heating deviation in the abnormal flow fluctuation ranges is low. Therefore, based on this, the number of time periods in the outdoor temperature range where the adjustment changes under the stated weather type do not meet the requirements is determined. When the proportion of the number of time periods in the outdoor temperature range where the adjustment changes under the stated weather type do not meet the requirements is greater than one-half, then temperature measurement points are identified and processed according to a preset time cycle in all outdoor temperature ranges where the adjustment changes of heating flow do not meet the requirements.

[0089] The connection with the preceding and following steps is only in Calculate on the interval and This ensures the identification and focusing of user-side deviations against the backdrop of abnormal fluctuations. Key quantities provided to S4: and its anomaly set The overlap relationship (used for determining the intensity of strategies under different weather types).

[0090] S4: Based on the overlap of the abnormal fluctuation flow ranges in different heating networks and the distribution of outdoor temperature ranges under different weather types, determine the identification and processing time period of the operating data of the heating network under different weather types.

[0091] Furthermore, the heating network operation data under different weather types includes data on annual temperatures categorized by... The step size is set to a set of target temperature points; the difference between the daily average outdoor temperature and the target point is less than... At that time, the current date will be assigned to the corresponding weather type. .

[0092] In each The following analysis summarizes the three types of indicators to derive a data analysis and processing strategy for the heating network operation, specifically including: Depend on The number of abnormal fluctuation flow intervals obtained from statistics is from The statistically obtained proportion of heating deviation intervals is from The percentage of adjustments that do not conform to the calculation is obtained by reverse calculation.

[0093] The data analysis strategy is dynamically adjusted based on weather type. Weather type classification and data mapping are used to generate target temperature sequences in 3°C increments. Daily classification: If the average outdoor temperature on a certain day... satisfy: Then the day is classified into weather types. . Label the corresponding date (or time period) interval { , , Mapped to each .

[0094] Calculate the number of outlier intervals for the indices (minimum sufficient set) within the type: Deviation range ratio The formula is expressed as: Adjustment not in proportion (1 = not at all, 0 = not at all) The formula is expressed as: The strategy determination rules include: Strategy A: High-intensity monitoring (dual pressure of insulation and heating) trigger: Then execute on all High-frequency measurement point identification is enabled in the interval (sampling / discrimination cycle 1 min); the adjustment side is used for the affected blocks. Set stricter adjustment and verification, the goal will be Increased to 1; Prioritize reviewing user-side metering / heat exchange links within the specified intervals, until... Descending to .

[0095] The operational data analysis strategy for dynamically adjusting the heating network based on weather changes includes classifying different weather types based on outdoor temperature data, combining historical operational data of the heating network, and analyzing and determining the optimal operational data analysis and processing strategy under different weather types.

[0096] The system automatically adjusts the heating network's regulation needs based on different weather conditions; when there are a large number of abnormal intervals and a high proportion of deviation intervals under a given weather type, it is defined as high-intensity monitoring, and all intervals under the current type are monitored. The flow range is subject to high-frequency monitoring and tightening control strategies.

[0097] When there are many abnormal intervals but the deviation ratio is low, targeted monitoring is defined based on the proportion of non-compliance adjustments; if the current proportion is higher than... If the temperature-flow ratio does not meet the criteria, then all non-compliant temperature-flow blocks will be covered; otherwise, enhancement measures will only be implemented within the time period corresponding to the current block. Implementation Strategy B: Targeted monitoring (significant temperature fluctuations but low user deviation) Triggering condition: Larger but not satisfied .

[0098] like Then in For all adjustments that do not conform to the block, Implement 1 minute high-frequency identification and adjustment verification.

[0099] like This will only be implemented during these non-compliance periods. If the interval between two non-compliance periods is greater than 1 hour, all non-compliance periods will be implemented within the interval. Periodic identification is added to the intervals to avoid blind spots.

[0100] Strategy C: Routine monitoring (overall good), triggering missed A / B. Maintain the strategy at a regular frequency; for sporadic cases... The blocks will initiate short-term enhanced sampling until they recover to 1. If the situation does not meet the criteria for high-intensity monitoring and targeted monitoring, the regular monitoring frequency will be maintained, and the evaluation model will be continuously updated with new data without changing the machine learning evaluation and threshold system.

[0101] It should be noted that weather types are classified based on outdoor temperature. Specifically, dates where the deviation of the outdoor temperature from the target weather type is less than 2 degrees Celsius are classified as the target weather type. The target weather type is based on the historical outdoor temperature of the heating network, with a 3-degree Celsius deviation as a baseline, and is further divided into multiple target weather types. When the proportion of time periods within the outdoor temperature range where the regulation changes under the weather type do not meet the requirements is not greater than half, temperature measurement point identification is prioritized within the outdoor temperature range where the regulation changes under the weather type do not meet the requirements. If the interval between two adjacent time periods within the outdoor temperature range where the regulation changes do not meet the requirements is greater than 1 hour, then temperature measurement point identification is performed on all abnormal flow fluctuation intervals between the two adjacent time periods within the outdoor temperature range where the regulation changes do not meet the requirements, according to a preset time period.

[0102] This embodiment also provides a system for analyzing and processing operational data of a heating network, including: The data acquisition and interval division module receives and cleans outdoor temperature, heating flow rate, and measuring point temperature, divides outdoor temperature intervals, and divides flow rate intervals at equal intervals according to historical ranges.

[0103] The abnormal fluctuation identification module is used to determine the range of abnormal fluctuations in flow, summarize the characteristics of adjustment events, and use a machine learning scoring function to evaluate whether the adjustment meets the requirements.

[0104] The heating deviation range identification module is used to calculate the deviation ratio and determine the heating deviation flow range by combining the actual heating user's actual heating capacity with the target heating capacity.

[0105] The weather type and strategy generation module summarizes the deviation ratio and adjustment non-compliance ratio indicators, and generates dynamic analysis and monitoring adjustment strategies based on threshold rules.

[0106] This embodiment also provides a computer device applicable to the method for analyzing and processing operational data of a heating pipeline network, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method for analyzing and processing operational data of a heating pipeline network as proposed in the above embodiment.

[0107] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0108] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the data analysis and processing method for the operation of a heating network as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0109] In summary, this invention achieves the following: Based on outdoor temperature monitoring data, it determines the operational variations of the heating network's monitoring data under different outdoor temperature ranges and different heating flow ranges; based on these operational variations, it determines the abnormal fluctuation flow range within the heating flow range; it determines historical adjustment data of the heating flow within the outdoor temperature range; based on this historical adjustment data, it calculates the heating deviation flow range when the adjustment variations of the heating flow within the outdoor temperature range meet the requirements; it determines the heating deviation flow range within the abnormal fluctuation flow range using historical operational data of the abnormal fluctuation flow ranges of different heating networks within the outdoor temperature range and the heating deviation of heat users within the abnormal fluctuation flow ranges; and it determines the identification and processing time period for the operational data of the heating network under different weather types by considering the overlap of the heating deviation flow ranges within the abnormal fluctuation flow ranges of different heating networks and the distribution of outdoor temperature ranges under different weather types.

[0110] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for analyzing and processing operational data of a heating network, characterized in that: This includes determining the operational changes of the monitoring data of the heating network under different outdoor temperature ranges and different heating flow ranges based on outdoor temperature monitoring data, and determining the abnormal fluctuation flow range in the heating flow range based on the operational changes. Determine the historical adjustment data of heating flow rate within the outdoor temperature range. Based on the historical adjustment data of heating flow rate, calculate the heating deviation flow rate range when the adjustment and change of heating flow rate within the outdoor temperature range meets the requirements. Based on the historical operating data of abnormal flow ranges of different heating pipe networks within the outdoor temperature range and the heating deviation of heat users within the abnormal flow range, the heating deviation flow range within the abnormal flow range is determined. Based on the overlap of heating deviation flow ranges within the abnormal fluctuation flow ranges of different heating networks, and combined with the distribution of outdoor temperature ranges under different weather types, the identification and processing time periods for the operating data of heating networks under different weather types are determined.

2. The method for analyzing and processing operational data of heating pipe networks as described in claim 1, characterized in that: The method based on outdoor temperature monitoring data includes collecting outdoor temperature time series data. Heating flow rate With each temperature measuring point , , Indicates the number of monitoring data points; performs basic cleaning and time alignment on outdoor temperature monitoring data; Based on outdoor temperature monitoring data, different outdoor temperature ranges and heating flow ranges are divided. Several flow ranges ,in Indicates the traffic range index; A two-dimensional grid of temperature-flow rate is obtained, and statistics and deviation calculations are performed within the grid. By analyzing the deviation of different temperature measuring points in the monitoring data, the temperature deviation is dynamically monitored, the operation and changes of the monitoring data in the region are analyzed, and abnormal intervals with significant fluctuations in the operation and changes of the heating flow rate are identified and automatically marked as abnormal fluctuation flow rate intervals.

3. The method for analyzing and processing operational data of a heating network as described in claim 2, characterized in that: The operational variations of the monitoring data under different heating flow ranges include dividing the outdoor temperature into several temperature ranges according to intervals. , Indicates a temperature range index; The historical heating flow range is divided into each block at equal intervals. Internally, summarize the data from each measuring point. Observe the temperature and take a robust statistic as the representative value of the current block; For the same flow range By comparing the range of representative values ​​at different temperature ranges, the temperature deviation of the measuring point within the flow rate range is obtained. ; Will The measuring points are marked as variable temperature measuring points; This indicates the temperature threshold that fluctuates across temperature ranges at the measuring point; it also counts the percentage of measuring points that change within the current flow range. ,by This reflects the operational changes within the current traffic range.

4. The method for analyzing and processing operational data of heating pipe networks as described in claim 3, characterized in that: The abnormal flow fluctuation range includes the determination of the heating deviation flow range within the abnormal flow fluctuation range based on the historical operating data of the abnormal flow fluctuation range of different heating pipe networks within the outdoor temperature range and the heating deviation of heat users within the abnormal flow fluctuation range. For each flow range If the proportion of measuring points changes Then the current traffic range will be marked as an abnormally fluctuating traffic range, and ; Obtain the anomaly set ; This indicates the safety threshold for abnormal fluctuations.

5. The method for analyzing and processing operational data of a heating network as described in claim 4, characterized in that: The heating deviation flow range includes, in each block Internally, it identifies historical regulation events, records the flow rate before and after each regulation, and calculates the regulation amount; the ratio of the regulation amount to the pre-regulation flow rate is greater than... Events are marked as adjustments that do not meet the requirements, and the percentage of adjustment events that do not meet the requirements within a block is calculated. ; This represents the abnormal adjustment threshold, obtained from historical operating data; The proportion of heating flow rate adjustments that meet or fail to meet requirements within the outdoor temperature range is used as the input feature. , ; Generate continuous scores for machine learning evaluation using a trained model. ;in accordance with Adjustment threshold for the determination block ; like If the requirements are met, the heating deviation flow range shall be determined when the adjustment and variation of the heating flow rate within the outdoor temperature range meets the requirements. The heating deviation of heat users is determined based on the deviation between the heating supply and the target heating supply within the abnormal fluctuation flow range; an LSTM model optimized based on the GWO algorithm is used to determine whether the adjustment and variation of the heating flow within the outdoor temperature range meets the requirements. The method for determining the heating deviation flow range within the abnormal fluctuation flow range is as follows: Based on the heating deviation of heat users within the abnormal flow fluctuation range, determine the deviation between the heating supply of heat users and the target heating supply within the abnormal flow fluctuation range; heat users whose deviation does not meet the requirements are identified as heat users with heating deviation. The number of heat users with heating deviations is used to determine whether the abnormal fluctuation flow range is a heating deviation flow range.

6. The method for analyzing and processing operational data of a heating network as described in claim 5, characterized in that: The distribution of outdoor temperature ranges under different weather types includes, according to the annual temperature... The step size is set to a set of target temperature points; the difference between the daily average outdoor temperature and the target point is less than... At that time, the current date will be assigned to the corresponding weather type. ; In each The following analysis summarizes the three types of indicators to derive a data analysis and processing strategy for the heating network operation, specifically including: Depend on The number of abnormal fluctuation flow intervals obtained from statistics is from The statistically obtained proportion of heating deviation flow ranges is derived from The percentage of adjustments that do not meet the requirements is calculated by reverse calculation.

7. The method for analyzing and processing operational data of a heating network as described in claim 6, characterized in that: The identification and processing period for heating network operation data under different weather types includes when the abnormal flow fluctuation range of the heating network highly overlaps with the heating deviation flow range, and the proportion of abnormal flow fluctuation ranges is higher than... If the insulation performance of the heating network is poor and the number of heat users with abnormal flow deviations is large within the abnormal flow range, then all weather types will fall within the abnormal flow range, and temperature measurement points will be identified and processed according to the preset time cycle.

8. A system for analyzing and processing operational data of a heating network, based on the method for analyzing and processing operational data of a heating network as described in any one of claims 1 to 7, characterized in that: include, The data acquisition and interval division module receives and cleans outdoor temperature, heating flow rate, and measuring point temperature, divides outdoor temperature intervals, and divides flow rate intervals at equal intervals according to historical ranges. The abnormal fluctuation identification module is used to determine the range of abnormal fluctuations in flow, summarize the characteristics of regulation events, and use machine learning scoring functions to evaluate whether the regulation meets the requirements. The heating deviation range identification module is used to combine the actual heating user's heat supply with the target heating supply, calculate the deviation ratio, and determine the heating deviation flow range. The weather type and strategy generation module summarizes the deviation ratio, adjusts non-compliant ratio indicators, and generates analysis and processing strategies for the operation data of the heating network under different weather types based on threshold rules.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the operation data analysis and processing method for heating pipe networks as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the operation data analysis and processing method for heating pipe networks as described in any one of claims 1 to 7.

Images