Primary heat supply pipe network energy efficiency evaluation system and method based on artificial intelligence

Abstract

The invention relates to the technical field of data processing, in particular to a primary heat supply pipe network energy efficiency evaluation system and method based on artificial intelligence, and the system comprises an acquisition module, a simulation module, a judgment module, a determination module, an output module, an adjustment module and an evaluation module. Key parameters are obtained in real time, and a conventional energy efficiency index is obtained based on data such as water supply temperature difference and flow and operation of a preset artificial intelligence model; abnormal sections are screened out layer by layer by using multi-dimensional parameters such as water conveying temperature difference, flow, bearing temperature, inlet pressure and vibration speed; quantifying the abnormal energy efficiency index; the preset parameters are dynamically optimized, so that the evaluation system can be adjusted in real time according to the actual operation condition; the energy efficiency level is obtained by integrating the adjusted data, accurate and timely energy efficiency evaluation of the primary heat supply pipe network is achieved, and the problem that the response speed of energy efficiency evaluation processing equipment is low due to excessive dependence on static data and a tedious calculation process is effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an artificial intelligence-based primary heating pipe network energy efficiency evaluation system and method. Background Art

[0002] With energy resources becoming increasingly scarce and environmental issues becoming increasingly prominent, energy conservation and emission reduction have become a global concern. As a major energy consumer, the heating industry can identify existing problems and energy-saving potential through energy efficiency evaluation, enabling appropriate measures to improve energy efficiency and reduce energy waste and pollutant emissions. This is crucial for achieving energy conservation and emission reduction goals. However, existing energy efficiency evaluation and processing equipment often has sparsely distributed data collection points, which cannot fully reflect the operating status of the entire heating network. Furthermore, the processing equipment struggles to quickly process the massive amount of data.

[0003] Patent document with publication number CN113007784A discloses a comprehensive evaluation method for a large-scale heating pipeline network, which includes: step 1, constructing a comprehensive evaluation system, including five evaluation objects, namely heating quality parameters, main energy consumption indicators, main equipment energy efficiency, main parameter control and intelligent control level; step 2, setting the evaluation indicators of each evaluation object in step 1; step 3, setting the evaluation criteria of each evaluation indicator of each evaluation object and scoring; step 4, calculating the evaluation score of each evaluation object, and weightedly accumulating the evaluation scores of the five evaluation objects to obtain the total comprehensive evaluation score of the large-scale heating pipeline network; step 5, performing a graded evaluation of the large-scale heating pipeline network according to the total comprehensive evaluation score of the large-scale heating pipeline network obtained in step 4.

[0004] It can be seen that the comprehensive evaluation method of large-scale heating pipeline networks has the following problems: large-scale heating pipeline networks are widely distributed, involving many equipment and monitoring points, and old equipment lacks an effective data acquisition system, resulting in incomplete or inaccurate data acquisition, affecting the reliability of the evaluation results; it involves multiple evaluation objects, multiple evaluation indicators, and complex weight calculations and weighted accumulation processes. The entire calculation process is relatively cumbersome and requires a lot of time and manpower for data processing and analysis; the operating conditions of large-scale heating pipeline networks are dynamically changing, and this method cannot timely and effectively adjust the evaluation system, resulting in the evaluation results being unable to timely reflect the actual operating status of the heating pipeline network. Summary of the Invention

[0005] To this end, the present invention provides an artificial intelligence-based primary heating pipeline energy efficiency evaluation system and method, which is used to overcome the problem of slow response speed of energy efficiency evaluation processing equipment in the existing technology due to excessive reliance on static data and cumbersome calculation processes through artificial intelligence models and dynamic adjustment mechanisms.

[0006] To achieve the above objectives, the present invention provides, on the one hand, an artificial intelligence-based primary heating network energy efficiency evaluation system, comprising:

[0007] The acquisition module is used to obtain in real time the water supply temperature difference, flow rate, transport water temperature difference, bearing temperature of the circulating water pump, inlet pressure and vibration speed of each section to be measured in the primary heating pipe network divided based on the preset length;

[0008] a simulation module connected to the acquisition module, configured to simulate and obtain a conventional energy efficiency index based on the water supply temperature difference, the flow rate, and a preset artificial intelligence model;

[0009] a determination module connected to the acquisition module, for determining a number of temporary sections based on the transport water temperature difference and the flow rate;

[0010] a determination module, connected to the acquisition module and the determination module respectively, for determining a number of abnormal sections according to the bearing temperature, the inlet pressure, the vibration speed and a preset correlation threshold of each temporary section;

[0011] an output module, connected to the acquisition module and the determination module respectively, for outputting an abnormal energy efficiency index based on the transport water temperature difference, the flow rate, the bearing temperature, the inlet pressure, and the vibration velocity of all the abnormal sections;

[0012] an adjustment module, connected to the output module and the simulation module respectively, for adjusting the preset length according to the abnormal energy efficiency index and the normal energy efficiency index to obtain an adjusted length, or adjusting the preset correlation threshold to obtain an adjusted correlation threshold;

[0013] An evaluation module is connected to the output module and the simulation module respectively, and is used to evaluate the primary heating network according to the abnormal energy efficiency index and the conventional energy efficiency index re-determined based on the adjustment length or the adjustment correlation threshold to obtain an energy efficiency grade.

[0014] Furthermore, the determination module includes:

[0015] a temperature difference comparison unit, for comparing the transported water temperature difference with a preset temperature difference threshold to obtain a temperature difference comparison result;

[0016] A determination unit is connected to the temperature difference comparison unit and is used to determine a number of temporary sections according to the flow rate when the temperature difference comparison result shows that the transport water temperature difference is greater than the preset temperature difference threshold.

[0017] Furthermore, the determination unit includes:

[0018] A flow fluctuation calculation subunit, configured to calculate a standard deviation of the flow within a preset determination time period to obtain a flow fluctuation value;

[0019] The determination subunit is connected to the flow fluctuation calculation subunit and is used to determine that the section to be tested is the temporary section when the flow fluctuation value is greater than a preset flow fluctuation threshold, so as to determine a plurality of temporary sections.

[0020] Furthermore, the determining module includes:

[0021] a temperature comparison unit, for comparing the bearing temperature with a preset temperature threshold to obtain a temperature comparison result;

[0022] a speed comparison unit connected to the temperature comparison unit, for comparing the vibration speed with a preset speed threshold to obtain a speed comparison result when the temperature comparison result indicates that the bearing temperature is greater than the preset temperature threshold;

[0023] A determination unit is connected to the speed comparison unit and is used to determine a number of abnormal sections according to the inlet pressure and vibration speed within a preset determination time period when the speed comparison result shows that the vibration speed is greater than the preset speed threshold.

[0024] Furthermore, the determining unit includes:

[0025] a normalization processing subunit, configured to perform normalization processing on all the inlet pressures to obtain a pressure normalized data set, and to perform normalization processing on all the vibration velocities to obtain a velocity normalized data set;

[0026] a correlation calculation subunit, connected to the normalization processing subunit, for calculating a correlation coefficient between the pressure normalized data set and the velocity normalized data set to obtain a change correlation;

[0027] The determination subunit is connected to the correlation calculation subunit and is used to determine that the temporary segment is the abnormal segment when the absolute value of the change correlation is greater than the preset correlation threshold, so as to determine a plurality of abnormal segments.

[0028] Furthermore, the output module includes:

[0029] an average value calculation unit, configured to calculate, within a preset calculation time period, an average value of the transport water temperature difference to obtain an average transport water temperature difference, and to calculate an average value of the flow rate to obtain an average flow rate, and to calculate an average value of the bearing temperature to obtain an average bearing temperature, and to calculate an average value of the inlet pressure to obtain an average inlet pressure, and to calculate an average value of the vibration velocity to obtain an average vibration velocity;

[0030] an index output unit connected to the mean value calculation unit, and configured to output an abnormal energy efficiency index based on the average transport water temperature difference, the average flow rate, the average bearing temperature, the average inlet pressure, the average vibration speed, a preset standard transport water temperature difference, a preset standard flow rate, a preset standard bearing temperature, a preset standard inlet pressure, a preset standard vibration speed, and a preset weight group.

[0031] Furthermore, the adjustment module includes:

[0032] an index deviation calculation unit, configured to calculate a relative deviation between the abnormal energy efficiency index and the normal energy efficiency index to obtain an index deviation;

[0033] An adjustment unit is connected to the index deviation calculation unit and is used to adjust the preset length according to the index deviation and a preset deviation range to obtain an adjusted length, or to adjust the preset correlation threshold to obtain an adjusted correlation threshold.

[0034] Furthermore, the adjustment unit includes:

[0035] a first adjustment subunit, configured to, when the exponential deviation is less than a minimum value of a preset deviation range, reduce the preset length according to a relative deviation between the exponential deviation and the minimum value of the preset deviation range and a preset length adjustment coefficient to obtain an adjusted length;

[0036] The second adjustment subunit is configured to reduce the preset correlation threshold according to the relative deviation between the index deviation and the maximum value of the preset deviation range and the preset correlation adjustment coefficient to obtain an adjusted correlation threshold when the index deviation is greater than the maximum value of the preset deviation range.

[0037] Furthermore, the evaluation module includes:

[0038] a ratio calculation unit, configured to calculate the ratio of the number of all abnormal sections to the number of all sections to be tested, to obtain an abnormal ratio;

[0039] an energy efficiency index calculation unit connected to the proportion calculation unit, and configured to determine, when the abnormal proportion is less than a preset proportion threshold, the conventional energy efficiency index as the overall energy efficiency index, or, when the abnormal proportion is greater than or equal to the preset proportion threshold, perform a weighted sum of the abnormal energy efficiency index, the conventional energy efficiency index, a preset abnormal weight, and a preset conventional weight to obtain an overall energy efficiency index;

[0040] an energy efficiency level determination unit connected to the energy efficiency index calculation unit, for determining the energy efficiency level as high efficiency when the overall energy efficiency index is greater than the maximum value of a preset energy efficiency range, for determining the energy efficiency level as low efficiency when the overall energy efficiency index is less than the minimum value of the preset energy efficiency range, and for determining the energy efficiency level as medium when the overall energy efficiency index is less than the maximum value of the preset energy efficiency range and the overall energy efficiency index is greater than the minimum value of the preset energy efficiency range.

[0041] On the other hand, the present invention also provides an artificial intelligence-based primary heating network energy efficiency evaluation method, comprising:

[0042] Real-time acquisition of water supply temperature difference, flow rate, transport water temperature difference, bearing temperature of circulating water pump, inlet pressure and vibration speed of each section to be tested in the primary heating pipe network divided based on preset length;

[0043] A conventional energy efficiency index is obtained based on the water supply temperature difference, the flow rate, and a preset artificial intelligence model simulation;

[0044] Determine a number of temporary sections based on the transport water temperature difference and the flow rate;

[0045] determining a plurality of abnormal sections according to the bearing temperature, the inlet pressure, the vibration velocity and a preset correlation threshold of each of the temporary sections;

[0046] Outputting an abnormal energy efficiency index according to the transport water temperature difference, the flow rate, the bearing temperature, the inlet pressure, and the vibration speed of all the abnormal sections;

[0047] Adjusting the preset length according to the abnormal energy efficiency index and the normal energy efficiency index to obtain an adjusted length, or adjusting the preset correlation threshold to obtain an adjusted correlation threshold;

[0048] The primary heating pipe network is evaluated according to the abnormal energy efficiency index and the normal energy efficiency index re-determined based on the adjustment length or the adjustment correlation threshold to obtain an energy efficiency grade.

[0049] Compared with the existing technology, the beneficial effects of the present invention are that, by obtaining key parameters in real time, the timeliness and comprehensiveness of the data are ensured; based on the water supply temperature difference, flow rate and other data and the preset artificial intelligence model calculation, a conventional energy efficiency index is obtained to provide a benchmark for subsequent comparison; using multi-dimensional parameters such as water supply temperature difference, flow rate, bearing temperature, inlet pressure, vibration speed, etc., abnormal sections are screened out layer by layer, closely fitting the data correlation between each parameter, from preliminary screening to precise positioning, to form a complete evaluation chain; quantifying the abnormal energy efficiency index and presenting the problem intuitively; dynamically optimizing the preset parameters so that the evaluation system can be adjusted in real time according to the actual operating conditions; the energy efficiency grade is obtained from the comprehensive adjusted data, realizing accurate, comprehensive and timely energy efficiency evaluation of the primary heating pipeline network, effectively solving the problem of slow response speed of energy efficiency evaluation processing equipment due to excessive reliance on static data and cumbersome calculation process.

[0050] Furthermore, by comparing the transported water temperature difference with a preset temperature difference threshold, we can quickly identify areas where anomalies may exist. This is because temperature differences are often a direct indicator of energy efficiency issues. When the transported water temperature difference exceeds the threshold, flow rate data is combined to determine a temporary section. This is because flow rate is directly related to heat transfer efficiency. Combining these two data points can more accurately identify specific sections with low energy efficiency.

[0051] Furthermore, the flow fluctuation value is obtained by calculating the standard deviation of the flow within the preset judgment time. When the fluctuation value exceeds the preset threshold, the section to be tested is determined to be a temporary section, which can effectively identify abnormal flow conditions. The standard deviation can quantify the stability of the flow, and abnormal fluctuations in the flow mean that the actual amount of heat medium transported deviates from the design or normal operating value, which will cause the heat to be unable to be transferred to the user end stably and efficiently as expected, affecting the quality of heating and reflecting energy efficiency issues.

[0052] Furthermore, by first comparing the bearing temperature to a preset temperature threshold and then, if the bearing temperature is too high, further checking whether the vibration velocity exceeds the preset speed threshold, the abnormal range is gradually narrowed and the abnormal section is accurately located. Because elevated bearing temperature and abnormal vibration velocity are often closely related to mechanical failure of the equipment, the comprehensive analysis of inlet pressure and vibration velocity can accurately identify abnormal conditions within a specific time period, ensuring timely detection of areas of energy efficiency reduction caused by equipment failure.

[0053] Furthermore, by calculating the correlation coefficient of the normalized pressure and velocity data sets, we obtain the variation correlation, which can quantify the strength of the linear relationship between the two parameters. When the absolute value of the variation correlation is greater than the preset correlation threshold, it indicates that the inlet pressure and vibration velocity are strongly positively or negatively correlated, provided that the vibration velocity is greater than the preset velocity threshold. On the one hand, a strong positive correlation indicates that when the system operates at high pressure, the vibration of the equipment is intensified, which may lead to increased energy loss and reduced equipment efficiency. On the other hand, a strong negative correlation indicates that the two change in opposite directions. When the vibration velocity increases, the inlet pressure decreases. When the inlet pressure drops below the vapor pressure of the liquid, the liquid vaporizes to form bubbles, causing cavitation. Cavitation can seriously disrupt the normal operation of the pump, reducing the head and flow rate, and increasing energy consumption.

[0054] Furthermore, by calculating the average values of water temperature difference, flow rate, bearing temperature, inlet pressure, and vibration velocity, data fluctuations can be effectively smoothed, reducing the impact of transient data anomalies on the evaluation results, and more stably and accurately reflecting the actual operating status of the heating network. The abnormal energy efficiency index is then calculated by combining preset standard parameters and weightings, ensuring the scientific and reliable evaluation results.

[0055] Furthermore, the rationality of the current preset length and preset correlation threshold is evaluated by calculating the relative deviation between the abnormal energy efficiency index and the normal energy efficiency index. If the deviation does not match the preset range, it indicates that the existing parameters cannot accurately reflect the actual energy efficiency status and need to be adjusted.

[0056] Furthermore, by reducing the preset length when the index deviation is less than the minimum value of the preset deviation range, the energy efficiency evaluation can be more focused on the key sections, thereby improving the evaluation accuracy; when the index deviation is greater than the maximum value of the preset deviation range, the preset correlation threshold is lowered, and the identification range of the abnormal sections is expanded to ensure that potential problems are not missed.

[0057] Furthermore, the overall energy efficiency index is determined by calculating the proportion of abnormal sections. When the abnormal proportion is less than the preset threshold, it means that the abnormal section accounts for a small proportion of the overall section to be tested, and the impact of the abnormal section on the overall energy efficiency is relatively small. The conventional energy efficiency index can more accurately reflect the overall operating status of the heating network, so the conventional energy efficiency index can represent the overall energy efficiency and simplify the calculation. When the abnormal proportion reaches or exceeds the threshold, the abnormal energy efficiency index is incorporated into the weighted sum to make the overall energy efficiency index more realistically reflect the actual energy efficiency of the system. The energy efficiency level is subsequently determined based on the comparison of the overall energy efficiency index with the preset range.

[0058] Furthermore, by acquiring key parameters in real time, the timeliness and comprehensiveness of the data are ensured; based on the water supply temperature difference, flow rate and other data and the preset artificial intelligence model calculation, a conventional energy efficiency index is obtained to provide a benchmark for subsequent comparisons; using multi-dimensional parameters such as water supply temperature difference, flow rate, bearing temperature, inlet pressure, vibration speed, etc., abnormal sections are screened out layer by layer, closely fitting the data correlation between each parameter, from preliminary screening to precise positioning, to form a complete evaluation chain; quantify the abnormal energy efficiency index and present the problem intuitively; dynamically optimize the preset parameters so that the evaluation system can be adjusted in real time according to the actual operating conditions; the energy efficiency level is obtained from the comprehensive adjusted data, realizing accurate, comprehensive and timely energy efficiency evaluation of the primary heating pipeline network, effectively solving the problem of slow response speed of energy efficiency evaluation processing equipment due to over-reliance on static data and cumbersome calculation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 Schematic diagram of the primary heating network energy efficiency evaluation system based on artificial intelligence in this embodiment;

[0060] Figure 2 FIG. 4 is a decision logic diagram for determining a temporary segment by the decision unit of this embodiment;

[0061] Figure 3 FIG. 1 is a decision logic diagram for determining an abnormal section for the determination unit of this embodiment;

[0062] Figure 4 This is a flow chart of the artificial intelligence-based primary heating network energy efficiency evaluation method of this embodiment. DETAILED DESCRIPTION

[0063] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0064] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0065] See also Figure 1 , which is a schematic diagram of the primary heating network energy efficiency evaluation system based on artificial intelligence in this embodiment;

[0066] On the one hand, this embodiment provides an artificial intelligence-based primary heating network energy efficiency evaluation system, including:

[0067] The acquisition module is used to obtain in real time the water supply temperature difference, flow rate, transport water temperature difference, bearing temperature of the circulating water pump, inlet pressure and vibration speed of each section to be measured in the primary heating pipe network divided based on the preset length;

[0068] a simulation module connected to the acquisition module, configured to simulate and obtain a conventional energy efficiency index based on the water supply temperature difference, the flow rate, and a preset artificial intelligence model;

[0069] a determination module connected to the acquisition module, for determining a number of temporary sections based on the transport water temperature difference and the flow rate;

[0070] a determination module, connected to the acquisition module and the determination module respectively, for determining a number of abnormal sections according to the bearing temperature, the inlet pressure, the vibration speed and a preset correlation threshold of each temporary section;

[0071] an output module, connected to the acquisition module and the determination module respectively, for outputting an abnormal energy efficiency index based on the transport water temperature difference, the flow rate, the bearing temperature, the inlet pressure, and the vibration velocity of all the abnormal sections;

[0072] an adjustment module, connected to the output module and the simulation module respectively, for adjusting the preset length according to the abnormal energy efficiency index and the normal energy efficiency index to obtain an adjusted length, or adjusting the preset correlation threshold to obtain an adjusted correlation threshold;

[0073] An evaluation module is connected to the output module and the simulation module respectively, and is used to evaluate the primary heating network according to the abnormal energy efficiency index and the conventional energy efficiency index re-determined based on the adjustment length or the adjustment correlation threshold to obtain an energy efficiency grade.

[0074] The acquisition module examines various data points within each test section, divided by preset lengths. These sections are specific pipe sections within the network, defined by preset lengths. They serve as the fundamental units for energy efficiency monitoring and evaluation. Each section includes key parameters such as supply water temperature differential, flow rate, transport water temperature differential, circulating water pump bearing temperature, inlet pressure, and vibration velocity. Real-time monitoring of these parameters enables accurate evaluation of the primary heating network's energy efficiency, providing a basis for energy efficiency optimization and energy conservation.

[0075] The supply water temperature difference is the difference between the supply water temperature and the return water temperature, reflecting the efficiency of heat energy transfer. By installing temperature sensors on the supply and return pipes of the primary heating network, the supply and return water temperatures can be measured in real time, and the supply water temperature difference can be calculated. Flow rate refers to the amount of fluid passing through a certain section of the pipeline per unit time. It is used to measure the transportation capacity of the heating system and can be measured with an electromagnetic flowmeter or an ultrasonic flowmeter. The transport water temperature difference refers to the difference between the inlet and outlet water temperatures when passing through the section. It is obtained by installing temperature sensors at the inlet and outlet of each section. Bearing temperature is an important indicator of the operating status of the circulating water pump. It reflects the friction and wear of the water pump bearings and is monitored by an infrared thermometer or temperature sensor directly installed on the bearing seat of the circulating water pump. The inlet pressure refers to the pressure at the inlet of the circulating water pump and can be measured by installing a pressure sensor at the inlet of the circulating water pump. The vibration velocity is used to measure the operating smoothness and mechanical condition of the circulating water pump and is monitored by installing a vibration sensor on the bearing seat of the circulating water pump.

[0076] The preset length refers to the length standard used to divide the sections to be measured in a primary heating network, pre-determined based on actual needs and specific circumstances. It depends on the scale and complexity of the heating network, monitoring requirements, total pipeline length, heating load distribution along the line, and equipment layout, and is typically set between 500 meters and 3 kilometers. In this example, it is set to 1000 meters, which can provide a more detailed reflection of the operating status of different sections without increasing monitoring costs and data processing complexity due to overly detailed divisions.

[0077] The preset correlation threshold is a standard value used to determine whether the correlation between inlet pressure and vibration velocity is significant. It depends on system characteristics and failure mode and is typically set between 0.7 and 0.95. In this embodiment, it is set to 0.8, which can effectively identify a significant correlation between inlet pressure and vibration velocity and accurately locate the abnormal section.

[0078] The preset artificial intelligence model is the long short-term memory network (LSTM) model, a recursive neural network that can process time series data. It is good at capturing temporal dependencies and is very suitable for analyzing energy efficiency data that changes over time in heating pipeline networks.

[0079] 1. Initial parameters:

[0080] Input characteristics: supply water temperature difference and flow rate.

[0081] Output: General energy efficiency index (a value between 0 and 1, where higher values indicate greater energy efficiency).

[0082] Model structure: The input layer receives water supply temperature difference and flow data; the hidden layer contains multiple LSTM units, which are responsible for capturing time series features; the output layer outputs the conventional energy efficiency index.

[0083] Hyperparameters: learning rate is 0.001, batch size is 32, and training period is 100 epochs.

[0084] 2. Training methods:

[0085] Data preparation: Collect historical heating data, including water supply temperature difference, flow rate, and corresponding energy efficiency labels. The energy efficiency label can be evaluated by experts or calculated based on historical data.

[0086] Data preprocessing: Normalize the data so that it is in the range of 0 to 1 to accelerate model convergence.

[0087] Model training: Use the training data to train the LSTM model, and update the model parameters through an optimization algorithm (such as Adam) to minimize the error between the predicted value and the actual value.

[0088] Validation and testing: Use the validation set to adjust hyperparameters to prevent overfitting; use the test set to evaluate model performance to ensure it has good generalization ability.

[0089] 3. Model after training:

[0090] Model saving: After training is completed, save the model parameters and structure for subsequent use.

[0091] Model evaluation: Record the performance indicators of the model on the training set, validation set and test set, such as mean square error (MSE) and coefficient of determination (R 2 ) to evaluate the accuracy and reliability of the model.

[0092] 4. Final output: For the input water supply temperature difference and flow data, the model outputs a value between 0 and 1, representing the corresponding conventional energy efficiency index.

[0093] By acquiring key data such as water supply temperature difference, flow, transport water temperature difference, bearing temperature of circulating water pump, inlet pressure and vibration speed in real time, and using the collected water supply temperature difference and flow data in combination with the preset artificial intelligence model for calculation, a conventional energy efficiency index reflecting normal operating conditions is simulated and obtained. Based on the transport water temperature difference and flow, several temporary sections are determined. The bearing temperature, inlet pressure, vibration speed and preset correlation threshold of each temporary section are further comprehensively considered to accurately determine the abnormal section. The abnormal energy efficiency index is calculated and output based on the relevant parameters of all abnormal sections. Based on the comparison results of the abnormal energy efficiency index and the conventional energy efficiency index, the preset length or correlation threshold is dynamically adjusted. The abnormal energy efficiency index and the conventional energy efficiency index are re-determined after the comprehensive adjustment of the parameters. Based on this, a comprehensive and accurate energy efficiency evaluation of the primary heating pipeline network is carried out to obtain the energy efficiency grade.

[0094] By acquiring key parameters in real time, the timeliness and comprehensiveness of the data are ensured; based on the water supply temperature difference, flow rate and other data and the preset artificial intelligence model calculation, a conventional energy efficiency index is obtained to provide a benchmark for subsequent comparisons; using multi-dimensional parameters such as water supply temperature difference, flow rate, bearing temperature, inlet pressure, vibration speed, etc., abnormal sections are screened out layer by layer, closely fitting the data correlation between each parameter, from preliminary screening to precise positioning, to form a complete evaluation chain; quantifying the abnormal energy efficiency index and presenting the problem intuitively; dynamically optimizing the preset parameters so that the evaluation system can be adjusted in real time according to the actual operating conditions; the energy efficiency level is obtained from the comprehensive adjusted data, realizing accurate, comprehensive and timely energy efficiency evaluation of the primary heating pipeline network, effectively solving the problem of slow response speed of energy efficiency evaluation processing equipment due to over-reliance on static data and cumbersome calculation processes.

[0095] Specifically, the determination module includes:

[0096] a temperature difference comparison unit, for comparing the transported water temperature difference with a preset temperature difference threshold to obtain a temperature difference comparison result;

[0097] A determination unit is connected to the temperature difference comparison unit and is used to determine a number of temporary sections according to the flow rate when the temperature difference comparison result shows that the transport water temperature difference is greater than the preset temperature difference threshold.

[0098] The preset temperature difference threshold is a standard value used to measure whether the temperature difference of water transported by the heating network is within the normal range. It depends on the characteristics of the heating medium, the insulation performance of the pipe network, and the user's heating needs, and is usually set between 5°C and 15°C. In this embodiment, it is set to 10°C, which can effectively distinguish between normal operation of the heating network and possible abnormal conditions.

[0099] By comparing the transport water temperature difference with the preset temperature difference threshold, a temperature difference comparison result is obtained; if the comparison result shows that the transport water temperature difference is greater than the preset temperature difference threshold, several temporary sections are further determined based on the flow rate.

[0100] By comparing the transported water temperature difference with a preset temperature difference threshold, we can quickly identify areas where anomalies may exist. This is because temperature differences are often a direct indicator of energy efficiency issues. When the transported water temperature difference exceeds the threshold, flow rate data is combined to determine a temporary section. This is because flow rate is directly related to heat transfer efficiency. Combining these two data points can more accurately identify specific sections with low energy efficiency.

[0101] Please continue reading Figure 2 As shown, it is a determination logic diagram of the determination unit of this embodiment for determining the temporary segment;

[0102] The determination unit includes:

[0103] A flow fluctuation calculation subunit, configured to calculate a standard deviation of the flow within a preset determination time period to obtain a flow fluctuation value;

[0104] The determination subunit is connected to the flow fluctuation calculation subunit and is used to determine that the section to be tested is the temporary section when the flow fluctuation value is greater than a preset flow fluctuation threshold, so as to determine a plurality of temporary sections.

[0105] The preset flow fluctuation threshold is a standard value used to judge whether the flow is abnormal. It depends on factors such as the scale of the heating network, operating conditions, and the performance of the water pump. It is usually set at 0.1m 3 / s to 0.3m 3 / s. In this embodiment, it is set to 0.15m 3 / s can not only sensitively capture abnormal fluctuations in traffic, but also avoid excessive misjudgments due to small fluctuations in normal operation.

[0106] The flow fluctuation value is obtained by calculating the standard deviation of the flow within the preset judgment time, and then the flow fluctuation value is compared with the preset flow fluctuation threshold. When the flow fluctuation value is greater than the preset flow fluctuation threshold, the section to be tested is determined to be a temporary section, thereby determining several temporary sections.

[0107] The flow fluctuation value is obtained by calculating the standard deviation of the flow within the preset judgment time. When the fluctuation value exceeds the preset threshold, the section to be tested is determined to be a temporary section, which can effectively identify abnormal flow conditions. The standard deviation can quantify the stability of the flow, and abnormal fluctuations in the flow mean that the actual amount of heat medium transported deviates from the design or normal operating value, which will cause the heat to be unable to be transferred to the user end stably and efficiently as expected, affecting the quality of heating and reflecting energy efficiency issues.

[0108] Specifically, the determination module includes:

[0109] a temperature comparison unit, for comparing the bearing temperature with a preset temperature threshold to obtain a temperature comparison result;

[0110] a speed comparison unit connected to the temperature comparison unit, for comparing the vibration speed with a preset speed threshold to obtain a speed comparison result when the temperature comparison result indicates that the bearing temperature is greater than the preset temperature threshold;

[0111] A determination unit is connected to the speed comparison unit and is used to determine a number of abnormal sections according to the inlet pressure and vibration speed within a preset determination time period when the speed comparison result shows that the vibration speed is greater than the preset speed threshold.

[0112] The preset temperature threshold is a standard value used to determine whether the circulating water pump bearing temperature is abnormal. It depends on the bearing model, pump operating conditions, and historical data, and is typically set between 70°C and 90°C. In this embodiment, it is set to 80°C, which can effectively identify bearing overheating and abnormal equipment operation.

[0113] The preset speed threshold is a standard value used to determine whether the circulating water pump's vibration speed is abnormal. It depends on the pump model, manufacturer's requirements, and site conditions, and is typically set between 3 mm / s and 8 mm / s. In this embodiment, it is set to 5 mm / s, which can promptly detect abnormal pump vibration, reduce mechanical failures, lower energy consumption, and improve energy efficiency.

[0114] The preset determination time is the length of time it takes to collect inlet pressure and vibration velocity data when determining the abnormal section. This time depends on the system's response speed, data stability, and the rate at which the abnormality develops, and is typically set between 30 seconds and 5 minutes. In this embodiment, it is set to 2 minutes, which allows for both sufficient data collection to ensure accurate determination and rapid identification of the abnormal section for timely processing.

[0115] The bearing temperature is compared with a preset temperature threshold to obtain a temperature comparison result. If the temperature comparison result indicates that the bearing temperature is greater than the preset temperature threshold, the vibration velocity is further compared with a preset velocity threshold to obtain a velocity comparison result. If the velocity comparison result indicates that the vibration velocity is greater than the preset velocity threshold, several abnormal sections are identified based on the inlet pressure and vibration velocity within a predetermined time period.

[0116] By first comparing the bearing temperature to a preset temperature threshold and then, if the bearing temperature is too high, further checking whether the vibration velocity exceeds the preset speed threshold, the abnormal range is gradually narrowed and the abnormal section is accurately located. Because elevated bearing temperature and abnormal vibration velocity are often closely related to mechanical failure of the equipment, the comprehensive analysis of inlet pressure and vibration velocity can accurately identify abnormal conditions within a specific time period, ensuring timely detection of areas where energy efficiency has decreased due to equipment failure.

[0117] Please continue reading Figure 3 As shown, it is a decision logic diagram of the determination unit in this embodiment for determining an abnormal section;

[0118] The determining unit includes:

[0119] a normalization processing subunit, configured to perform normalization processing on all the inlet pressures to obtain a pressure normalized data set, and to perform normalization processing on all the vibration velocities to obtain a velocity normalized data set;

[0120] a correlation calculation subunit, connected to the normalization processing subunit, for calculating a correlation coefficient between the pressure normalized data set and the velocity normalized data set to obtain a change correlation;

[0121] The determination subunit is connected to the correlation calculation subunit and is used to determine that the temporary segment is the abnormal segment when the absolute value of the change correlation is greater than the preset correlation threshold, so as to determine a plurality of abnormal segments.

[0122] All inlet pressures are normalized to obtain a pressure-normalized dataset, while all vibration velocities are normalized to obtain a velocity-normalized dataset. Next, the correlation coefficient between these two normalized datasets is calculated to obtain the variation correlation. Finally, if the absolute value of the variation correlation exceeds a preset correlation threshold, the corresponding temporary segment is determined to be an abnormal segment, thereby identifying multiple abnormal segments.

[0123] By calculating the correlation coefficient of the normalized pressure and velocity data sets, we obtain the variation correlation, which quantifies the strength of the linear relationship between the two parameters. When the absolute value of the variation correlation is greater than the preset correlation threshold, it indicates that the inlet pressure and vibration velocity are strongly positively or negatively correlated, provided that the vibration velocity is greater than the preset velocity threshold. On the one hand, a strong positive correlation indicates that the vibration of the equipment is intensified when the system operates at high pressure, which may lead to increased energy loss and reduced equipment efficiency. On the other hand, a strong negative correlation indicates that the two change in opposite directions. When the vibration velocity increases, the inlet pressure decreases. When the inlet pressure drops below the vapor pressure of the liquid, the liquid vaporizes and forms bubbles, causing cavitation. Cavitation can seriously disrupt the normal operation of the pump, reducing the head and flow rate, and increasing energy consumption.

[0124] Specifically, the output module includes:

[0125] an average value calculation unit, configured to calculate, within a preset calculation time period, an average value of the transport water temperature difference to obtain an average transport water temperature difference, and to calculate an average value of the flow rate to obtain an average flow rate, and to calculate an average value of the bearing temperature to obtain an average bearing temperature, and to calculate an average value of the inlet pressure to obtain an average inlet pressure, and to calculate an average value of the vibration velocity to obtain an average vibration velocity;

[0126] an index output unit connected to the mean value calculation unit, and configured to output an abnormal energy efficiency index based on the average transport water temperature difference, the average flow rate, the average bearing temperature, the average inlet pressure, the average vibration speed, a preset standard transport water temperature difference, a preset standard flow rate, a preset standard bearing temperature, a preset standard inlet pressure, a preset standard vibration speed, and a preset weight group.

[0127] Abnormal energy efficiency index calculation formula:

[0128]

[0129] Where: A: abnormal energy efficiency index; n: the number of abnormal segments; i: the i-th abnormal segment;

[0130] △T 运，i : the average transport water temperature difference of the i-th abnormal section;

[0131] Q i : the average flow rate of the ith abnormal section;

[0132] T 轴承，i : average bearing temperature of the ith abnormal section;

[0133] P 进口，i : the average inlet pressure of the ith abnormal section;

[0134] V 振动，i : average vibration velocity of the ith abnormal section;

[0135] w1: preset temperature difference weight; w2: preset flow weight; w3: preset temperature weight;

[0136] w4: preset pressure weight; w5: preset speed weight;

[0137] △T 运，设 : Preset standard transport water temperature difference;

[0138] Q 设 : Preset standard flow;

[0139] T 轴承，设 : Preset standard bearing temperature;

[0140] P 进口，设 : Preset standard inlet pressure;

[0141] V 振动，设 : Preset standard vibration speed.

[0142] The preset weight group includes: a preset temperature difference weight, a preset flow weight, a preset temperature weight, a preset pressure weight, and a preset speed weight, and the sum of all weights is 1.

[0143] The preset temperature difference weight is the weight of the transport water temperature difference when calculating the abnormal energy efficiency index. It depends on the degree of impact of the transport water temperature difference on energy efficiency and is usually set between 0.2 and 0.4. In this embodiment, it is set to 0.3 to reasonably reflect the impact of the transport water temperature difference on energy efficiency and ensure accurate evaluation results.

[0144] The preset traffic weight is the weight of traffic when calculating the abnormal energy efficiency index. It depends on the impact of traffic on energy efficiency and is usually set between 0.2 and 0.4. In this embodiment, it is set to 0.25 to accurately reflect the impact of traffic on energy efficiency and ensure the reliability of the evaluation results.

[0145] The preset temperature weight is the weight given to bearing temperature when calculating the abnormal energy efficiency index. It depends on the degree of bearing temperature's impact on energy efficiency and is typically set between 0.1 and 0.3. In this example, it is set to 0.15, effectively reflecting the impact of bearing temperature on energy efficiency and ensuring the accuracy of the evaluation results.

[0146] The preset pressure weight is the weight of inlet pressure when calculating the abnormal energy efficiency index. It depends on the degree of impact of inlet pressure on energy efficiency and is usually set between 0.1 and 0.3. In this embodiment, it is set to 0.15 to reasonably reflect the impact of inlet pressure on energy efficiency and ensure accurate evaluation results.

[0147] The preset speed weight is the weight of vibration speed when calculating the abnormal energy efficiency index. It depends on the degree of impact of vibration speed on energy efficiency and is usually set between 0.1 and 0.3. In this embodiment, it is set to 0.15, which effectively reflects the impact of vibration speed on energy efficiency and ensures the reliability of the evaluation results.

[0148] The preset standard transport water temperature difference is a benchmark transport water temperature difference for comparison, which depends on the transport water temperature difference under ideal operating conditions and is usually set between 5° C. and 15° C. In this embodiment, it is set to 10° C. to facilitate accurate assessment of the abnormality of the transport water temperature difference.

[0149] The preset standard flow rate is the benchmark flow rate for comparison, which depends on the flow rate under ideal operating conditions and is usually set at 30m 3 / h to 100m 3 / h. In this embodiment, it is set to 50m 3 / h, which is convenient for accurately evaluating the abnormal degree of flow.

[0150] The preset standard bearing temperature is a reference bearing temperature for comparison, which depends on the bearing temperature under ideal operating conditions and is generally set between 50° C. and 70° C. In this embodiment, it is set to 60° C. to facilitate accurate assessment of the abnormality of the bearing temperature.

[0151] The preset standard inlet pressure is a reference inlet pressure for comparison, which depends on the inlet pressure under ideal operating conditions and is usually set between 0.3 MPa and 1.0 MPa. In this embodiment, it is set to 0.5 MPa to facilitate accurate assessment of the degree of abnormality in the inlet pressure.

[0152] The preset standard vibration velocity is a baseline vibration velocity for comparison, which depends on the vibration velocity under ideal operating conditions and is generally set between 1 mm / s and 5 mm / s. In this embodiment, it is set to 3 mm / s to facilitate accurate assessment of the degree of abnormality in the vibration velocity.

[0153] The preset calculation time is the time period set when calculating the average value of each parameter. It depends on the operating characteristics of the heating system and the stability of data changes. It is usually set between 30 seconds and 5 minutes. In this embodiment, it is set to 3 minutes to ensure the representativeness and timeliness of the data.

[0154] By calculating the average values of the water transport temperature difference, flow rate, bearing temperature, inlet pressure, and vibration velocity over a preset calculation time, we obtain the average water transport temperature difference, average flow rate, average bearing temperature, average inlet pressure, and average vibration velocity, respectively. Then, based on these average values and the preset standard parameters and weightings, the Abnormal Energy Efficiency Index calculation formula is used to calculate and output the Abnormal Energy Efficiency Index.

[0155] By calculating the average values of water temperature difference, flow rate, bearing temperature, inlet pressure, and vibration velocity, data fluctuations can be effectively smoothed, reducing the impact of transient data anomalies on evaluation results, and more stably and accurately reflecting the actual operating status of the heating network. The abnormal energy efficiency index is then calculated using pre-set standard parameters and weightings, ensuring the scientific and reliable evaluation results.

[0156] Specifically, the adjustment module includes:

[0157] an index deviation calculation unit, configured to calculate a relative deviation between the abnormal energy efficiency index and the normal energy efficiency index to obtain an index deviation;

[0158] An adjustment unit is connected to the index deviation calculation unit and is used to adjust the preset length according to the index deviation and a preset deviation range to obtain an adjusted length, or to adjust the preset correlation threshold to obtain an adjusted correlation threshold.

[0159] The preset deviation range is a standard interval used to determine whether the relative deviation between the abnormal energy efficiency index and the normal energy efficiency index exceeds the normal range. It depends on the energy efficiency fluctuation tolerance of the system design, the statistical analysis of historical operating data, and the accuracy requirements of the energy efficiency evaluation. It is usually set between 5% and 20%. In this embodiment, it is set to 10%, which effectively balances the sensitivity and stability of system adjustments and allows timely adjustment of evaluation parameters to optimize evaluation results.

[0160] The relative deviation between the abnormal energy efficiency index and the normal energy efficiency index is calculated to obtain an index deviation, and then, based on the index deviation and a preset deviation range, the preset length or the preset correlation threshold is adjusted.

[0161] The rationality of the current preset length and preset correlation threshold is evaluated by calculating the relative deviation between the abnormal energy efficiency index and the normal energy efficiency index. If the deviation does not match the preset range, it indicates that the existing parameters cannot accurately reflect the actual energy efficiency status and need to be adjusted.

[0162] Specifically, the adjustment unit includes:

[0163] a first adjustment subunit, configured to, when the exponential deviation is less than a minimum value of a preset deviation range, reduce the preset length according to a relative deviation between the exponential deviation and the minimum value of the preset deviation range and a preset length adjustment coefficient to obtain an adjusted length;

[0164] The second adjustment subunit is configured to reduce the preset correlation threshold according to the relative deviation between the index deviation and the maximum value of the preset deviation range and the preset correlation adjustment coefficient to obtain an adjusted correlation threshold when the index deviation is greater than the maximum value of the preset deviation range.

[0165] The preset length adjustment coefficient is a factor used to adjust the preset length. It depends on the system's sensitivity to length adjustment and historical data, and is typically set between 0.8 and 0.95. In this embodiment, it is set to 0.9, which effectively reduces the preset length while avoiding excessive adjustments.

[0166] The preset relevance adjustment factor is a modulating factor used to adjust the preset relevance threshold. It depends on the system's sensitivity to relevance adjustments and historical data, and is typically set between 0.8 and 0.95. In this embodiment, it is set to 0.85, which effectively reduces the preset relevance threshold while avoiding excessive adjustments that could lead to inaccurate results.

[0167] When the index deviation is less than the minimum value of the preset deviation range, the preset length is reduced according to the relative deviation between the index deviation and the minimum value and the preset length adjustment coefficient to obtain the adjusted length; when the index deviation is greater than the maximum value of the preset deviation range, the preset correlation threshold is reduced according to the relative deviation between the index deviation and the maximum value and the preset correlation adjustment coefficient to obtain the adjusted correlation threshold.

[0168] By reducing the preset length when the index deviation is less than the minimum value of the preset deviation range, the energy efficiency evaluation can be more focused on the key sections, thereby improving the evaluation accuracy; when the index deviation is greater than the maximum value of the preset deviation range, the preset correlation threshold is lowered, and the identification range of abnormal sections is expanded to ensure that potential problems are not missed.

[0169] Specifically, the evaluation module includes:

[0170] a ratio calculation unit, configured to calculate the ratio of the number of all abnormal sections to the number of all sections to be tested, to obtain an abnormal ratio;

[0171] an energy efficiency index calculation unit connected to the proportion calculation unit, and configured to determine, when the abnormal proportion is less than a preset proportion threshold, the conventional energy efficiency index as the overall energy efficiency index, or, when the abnormal proportion is greater than or equal to the preset proportion threshold, perform a weighted sum of the abnormal energy efficiency index, the conventional energy efficiency index, a preset abnormal weight, and a preset conventional weight to obtain an overall energy efficiency index;

[0172] an energy efficiency level determination unit connected to the energy efficiency index calculation unit, for determining the energy efficiency level as high efficiency when the overall energy efficiency index is greater than the maximum value of a preset energy efficiency range, for determining the energy efficiency level as low efficiency when the overall energy efficiency index is less than the minimum value of the preset energy efficiency range, and for determining the energy efficiency level as medium when the overall energy efficiency index is less than the maximum value of the preset energy efficiency range and the overall energy efficiency index is greater than the minimum value of the preset energy efficiency range.

[0173] The preset percentage threshold is a standard value used to determine whether the number of abnormal sections is significant. It depends on the overall reliability of the system and its tolerance for abnormalities and is usually set between 0.1 and 0.3. In this embodiment, it is set to 0.15 to reasonably distinguish between normal and abnormal states and ensure the accuracy of energy efficiency evaluation.

[0174] The preset abnormality weight refers to the weight of the abnormal energy efficiency index when calculating the overall energy efficiency index. It depends on the degree of impact of the abnormal section on the overall energy efficiency and is usually set between 0.5 and 0.8. In this embodiment, it is set to 0.6 to highlight the impact of the abnormal section on the overall energy efficiency and ensure the sensitivity of the evaluation results.

[0175] The preset conventional weight refers to the weight of the conventional energy efficiency index when calculating the overall energy efficiency index. It depends on the contribution of the conventional operating section to the overall energy efficiency and is usually set between 0.2 and 0.5. In this embodiment, it is set to 0.4 to reasonably reflect the basic contribution of the conventional section to the overall energy efficiency and ensure a balanced evaluation result.

[0176] The preset energy efficiency range is a benchmark range for determining energy efficiency levels, which is determined by industry standards and actual operating experience and is typically set between 0.5 and 0.9. In this embodiment, it is set to [0.6, 0.8] to provide a clear energy efficiency level division, facilitating management and decision-making.

[0177] The abnormality ratio is calculated by calculating the ratio of the number of all abnormal sections to the number of all sections to be tested. If the abnormality ratio is less than the preset ratio threshold, the conventional energy efficiency index is determined to be the overall energy efficiency index; if the abnormality ratio is greater than or equal to the preset ratio threshold, the abnormal energy efficiency index and the conventional energy efficiency index are weighted and summed, and the overall energy efficiency index is calculated by combining the preset abnormal weight and the preset conventional weight. Finally, the energy efficiency level is determined based on the comparison between the overall energy efficiency index and the preset energy efficiency range: if the overall energy efficiency index is greater than the maximum value of the preset energy efficiency range, the energy efficiency level is determined to be high efficiency; if the overall energy efficiency index is less than the minimum value of the preset energy efficiency range, the energy efficiency level is determined to be low efficiency; if the overall energy efficiency index is between the minimum and maximum values of the preset energy efficiency range, the energy efficiency level is determined to be medium.

[0178] The overall energy efficiency index is determined by calculating the proportion of abnormal sections. When the abnormal proportion is less than the preset threshold, it means that the abnormal section accounts for a small proportion of the overall section to be tested, and the impact of the abnormal section on the overall energy efficiency is relatively small. The conventional energy efficiency index can more accurately reflect the overall operating status of the heating network, so the conventional energy efficiency index can represent the overall energy efficiency and simplify the calculation. When the abnormal proportion reaches or exceeds the threshold, the abnormal energy efficiency index is incorporated into the weighted sum to make the overall energy efficiency index more realistically reflect the actual energy efficiency of the system. The energy efficiency level is subsequently determined based on the comparison of the overall energy efficiency index with the preset range.

[0179] Please continue reading Figure 4 As shown, it is a flow chart of the energy efficiency evaluation method of the primary heating network based on artificial intelligence in this embodiment;

[0180] On the other hand, this embodiment also provides an artificial intelligence-based primary heating network energy efficiency evaluation method, including:

[0181] Real-time acquisition of water supply temperature difference, flow rate, transport water temperature difference, bearing temperature of circulating water pump, inlet pressure and vibration speed of each section to be tested in the primary heating pipe network divided based on preset length;

[0182] A conventional energy efficiency index is obtained based on the water supply temperature difference, the flow rate, and a preset artificial intelligence model simulation;

[0183] Determine a number of temporary sections based on the transport water temperature difference and the flow rate;

[0184] determining a plurality of abnormal sections according to the bearing temperature, the inlet pressure, the vibration velocity and a preset correlation threshold of each of the temporary sections;

[0185] Outputting an abnormal energy efficiency index according to the transport water temperature difference, the flow rate, the bearing temperature, the inlet pressure, and the vibration speed of all the abnormal sections;

[0186] Adjusting the preset length according to the abnormal energy efficiency index and the normal energy efficiency index to obtain an adjusted length, or adjusting the preset correlation threshold to obtain an adjusted correlation threshold;

[0187] The primary heating pipe network is evaluated according to the abnormal energy efficiency index and the normal energy efficiency index re-determined based on the adjustment length or the adjustment correlation threshold to obtain an energy efficiency grade.

[0188] By acquiring key data such as water supply temperature difference, flow, transport water temperature difference, bearing temperature of circulating water pump, inlet pressure and vibration speed in real time, the conventional energy efficiency index is obtained based on the water supply temperature difference and flow data and combined with the artificial intelligence model simulation, and several temporary sections are determined according to the transport water temperature difference and flow. The bearing temperature, inlet pressure, vibration speed and preset correlation threshold of each temporary section are further comprehensively considered to accurately determine the abnormal section. The abnormal energy efficiency index is calculated and output based on the relevant parameters of all abnormal sections. According to the comparison results of the abnormal energy efficiency index and the conventional energy efficiency index, the preset length or correlation threshold is dynamically adjusted. The abnormal energy efficiency index and the conventional energy efficiency index are re-determined based on the comprehensively adjusted parameters. Based on this, a comprehensive and accurate energy efficiency evaluation of the primary heating pipeline network is carried out to obtain the energy efficiency grade.

[0189] By acquiring key parameters in real time, the timeliness and comprehensiveness of the data are ensured; based on the water supply temperature difference, flow rate and other data and the preset artificial intelligence model calculation, a conventional energy efficiency index is obtained to provide a benchmark for subsequent comparisons; using multi-dimensional parameters such as water supply temperature difference, flow rate, bearing temperature, inlet pressure, vibration speed, etc., abnormal sections are screened out layer by layer, closely fitting the data correlation between each parameter, from preliminary screening to precise positioning, to form a complete evaluation chain; quantifying the abnormal energy efficiency index and presenting the problem intuitively; dynamically optimizing the preset parameters so that the evaluation system can be adjusted in real time according to the actual operating conditions; the energy efficiency level is obtained from the comprehensive adjusted data, realizing accurate, comprehensive and timely energy efficiency evaluation of the primary heating pipeline network, effectively solving the problem of slow response speed of energy efficiency evaluation processing equipment due to over-reliance on static data and cumbersome calculation processes.

[0190] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. An artificial intelligence-based primary heating network energy efficiency evaluation system and method, characterized in that: include: The acquisition module is used to obtain in real time the water supply temperature difference, flow rate, transport water temperature difference, bearing temperature of the circulating water pump, inlet pressure and vibration speed of each section to be measured in the primary heating pipe network divided based on the preset length; a simulation module connected to the acquisition module, configured to simulate and obtain a conventional energy efficiency index based on the water supply temperature difference, the flow rate, and a preset artificial intelligence model; a determination module connected to the acquisition module, for determining a number of temporary sections based on the transport water temperature difference and the flow rate; a determination module, connected to the acquisition module and the determination module respectively, for determining a number of abnormal sections according to the bearing temperature, the inlet pressure, the vibration speed and a preset correlation threshold of each temporary section; an output module, connected to the acquisition module and the determination module respectively, for outputting an abnormal energy efficiency index based on the transport water temperature difference, the flow rate, the bearing temperature, the inlet pressure, and the vibration velocity of all the abnormal sections; an adjustment module, connected to the output module and the simulation module respectively, for adjusting the preset length according to the abnormal energy efficiency index and the normal energy efficiency index to obtain an adjusted length, or adjusting the preset correlation threshold to obtain an adjusted correlation threshold; An evaluation module is connected to the output module and the simulation module respectively, and is used to evaluate the primary heating network according to the abnormal energy efficiency index and the conventional energy efficiency index re-determined based on the adjustment length or the adjustment correlation threshold to obtain an energy efficiency grade.

2. The artificial intelligence-based primary heating network energy efficiency evaluation system according to claim 1 is characterized in that: The determination module includes: a temperature difference comparison unit, for comparing the transported water temperature difference with a preset temperature difference threshold to obtain a temperature difference comparison result; A determination unit is connected to the temperature difference comparison unit and is used to determine a number of temporary sections according to the flow rate when the temperature difference comparison result shows that the transport water temperature difference is greater than the preset temperature difference threshold.

3. The artificial intelligence-based primary heating network energy efficiency evaluation system according to claim 2 is characterized in that: The determination unit includes: A flow fluctuation calculation subunit, configured to calculate a standard deviation of the flow within a preset determination time period to obtain a flow fluctuation value; The determination subunit is connected to the flow fluctuation calculation subunit and is used to determine that the section to be tested is the temporary section when the flow fluctuation value is greater than a preset flow fluctuation threshold, so as to determine a plurality of temporary sections.

4. The artificial intelligence-based primary heating network energy efficiency evaluation system according to claim 3 is characterized in that: The determination module includes: a temperature comparison unit, for comparing the bearing temperature with a preset temperature threshold to obtain a temperature comparison result; a speed comparison unit connected to the temperature comparison unit, for comparing the vibration speed with a preset speed threshold to obtain a speed comparison result when the temperature comparison result indicates that the bearing temperature is greater than the preset temperature threshold; A determination unit is connected to the speed comparison unit and is used to determine a number of abnormal sections according to the inlet pressure and vibration speed within a preset determination time period when the speed comparison result shows that the vibration speed is greater than the preset speed threshold.

5. The artificial intelligence-based primary heating network energy efficiency evaluation system according to claim 4 is characterized in that: The determining unit includes: a normalization processing subunit, configured to perform normalization processing on all the inlet pressures to obtain a pressure normalized data set, and to perform normalization processing on all the vibration velocities to obtain a velocity normalized data set; a correlation calculation subunit, connected to the normalization processing subunit, for calculating a correlation coefficient between the pressure normalized data set and the velocity normalized data set to obtain a change correlation; The determination subunit is connected to the correlation calculation subunit and is used to determine that the temporary segment is the abnormal segment when the absolute value of the change correlation is greater than the preset correlation threshold, so as to determine a plurality of abnormal segments.

6. The artificial intelligence-based primary heating network energy efficiency evaluation system according to claim 5 is characterized in that: The output module includes: an average value calculation unit, configured to calculate, within a preset calculation time period, an average value of the transport water temperature difference to obtain an average transport water temperature difference, and to calculate an average value of the flow rate to obtain an average flow rate, and to calculate an average value of the bearing temperature to obtain an average bearing temperature, and to calculate an average value of the inlet pressure to obtain an average inlet pressure, and to calculate an average value of the vibration velocity to obtain an average vibration velocity; an index output unit connected to the mean value calculation unit, and configured to output an abnormal energy efficiency index based on the average transport water temperature difference, the average flow rate, the average bearing temperature, the average inlet pressure, the average vibration speed, a preset standard transport water temperature difference, a preset standard flow rate, a preset standard bearing temperature, a preset standard inlet pressure, a preset standard vibration speed, and a preset weight group.

7. The artificial intelligence-based primary heating network energy efficiency evaluation system according to claim 6, characterized in that: The adjustment module includes: An index deviation calculation unit, configured to calculate a relative deviation between the abnormal energy efficiency index and the normal energy efficiency index to obtain an index deviation; An adjustment unit is connected to the index deviation calculation unit and is used to adjust the preset length according to the index deviation and a preset deviation range to obtain an adjusted length, or to adjust the preset correlation threshold to obtain an adjusted correlation threshold.

8. The artificial intelligence-based primary heating network energy efficiency evaluation system according to claim 7 is characterized in that: The adjustment unit includes: a first adjustment subunit, configured to, when the exponential deviation is less than a minimum value of a preset deviation range, reduce the preset length according to a relative deviation between the exponential deviation and the minimum value of the preset deviation range and a preset length adjustment coefficient to obtain an adjusted length; The second adjustment subunit is configured to reduce the preset correlation threshold according to the relative deviation between the index deviation and the maximum value of the preset deviation range and the preset correlation adjustment coefficient to obtain an adjusted correlation threshold when the index deviation is greater than the maximum value of the preset deviation range.

9. The artificial intelligence-based primary heating network energy efficiency evaluation system according to claim 8, characterized in that: The evaluation module includes: a ratio calculation unit, configured to calculate the ratio of the number of all abnormal sections to the number of all sections to be tested, to obtain an abnormal ratio; an energy efficiency index calculation unit connected to the proportion calculation unit, and configured to determine, when the abnormal proportion is less than a preset proportion threshold, the conventional energy efficiency index as the overall energy efficiency index, or, when the abnormal proportion is greater than or equal to the preset proportion threshold, perform a weighted sum of the abnormal energy efficiency index, the conventional energy efficiency index, a preset abnormal weight, and a preset conventional weight to obtain an overall energy efficiency index; an energy efficiency level determination unit connected to the energy efficiency index calculation unit, for determining the energy efficiency level as high efficiency when the overall energy efficiency index is greater than the maximum value of a preset energy efficiency range, for determining the energy efficiency level as low efficiency when the overall energy efficiency index is less than the minimum value of the preset energy efficiency range, and for determining the energy efficiency level as medium when the overall energy efficiency index is less than the maximum value of the preset energy efficiency range and the overall energy efficiency index is greater than the minimum value of the preset energy efficiency range.

10. An artificial intelligence-based primary heating network energy efficiency evaluation method, based on the artificial intelligence-based primary heating network energy efficiency evaluation system according to claims 1-9, characterized in that: include: Real-time acquisition of water supply temperature difference, flow rate, transport water temperature difference, bearing temperature of circulating water pump, inlet pressure and vibration speed of each section to be tested in the primary heating pipe network divided based on preset length; A conventional energy efficiency index is obtained based on the water supply temperature difference, the flow rate, and a preset artificial intelligence model simulation; Determine a number of temporary sections based on the transport water temperature difference and the flow rate; determining a plurality of abnormal sections according to the bearing temperature, the inlet pressure, the vibration velocity and a preset correlation threshold of each of the temporary sections; Outputting an abnormal energy efficiency index according to the transport water temperature difference, the flow rate, the bearing temperature, the inlet pressure, and the vibration speed of all the abnormal sections; Adjusting the preset length according to the abnormal energy efficiency index and the normal energy efficiency index to obtain an adjusted length, or adjusting the preset correlation threshold to obtain an adjusted correlation threshold; The primary heating pipe network is evaluated according to the abnormal energy efficiency index and the normal energy efficiency index re-determined based on the adjustment length or the adjustment correlation threshold to obtain an energy efficiency grade.

Images