A heat exchange station fault diagnosis method and device, electronic equipment and storage medium

Abstract

This application provides a method, apparatus, electronic device, and storage medium for fault diagnosis of heat exchange stations. The method includes acquiring real-time operating parameters and environmental parameters of the heat exchange station; dynamically correcting preset rated operating parameters of the heat exchange station based on the environmental parameters to obtain dynamic benchmark thresholds corresponding to each real-time operating parameter; determining preset fault characteristic values ​​in multiple dimensions based on the deviation between the real-time operating parameters and the corresponding dynamic benchmark thresholds; and determining the target fault source based on the determined fault characteristic values ​​in multiple dimensions and the preset mapping relationship between fault characteristics and fault sources. This invention calculates dynamic correction coefficients based on environmental parameters and uses these coefficients to correct rated operating parameters to generate dynamic benchmark thresholds. This allows the fault determination benchmark to adaptively adjust in real-time according to changes in the external environment and internal load, improving the environmental adaptability and accuracy of fault diagnosis.

Description

Technical Field

[0001] This invention relates to the field of intelligent operation and maintenance technology for centralized heating, and more specifically, to a method, device, electronic equipment, and storage medium for diagnosing faults in heat exchange stations. Background Technology

[0002] In centralized heating systems, heat exchange stations, as the core nodes for heat exchange and distribution, directly affect the quality and safety of heating. Currently, fault monitoring of heat exchange stations mainly relies on manually set fixed threshold alarm mechanisms, which trigger an alarm when a single operating parameter such as temperature, pressure, or flow rate exceeds preset static upper or lower limits. However, the actual operating conditions of heat exchange stations change dynamically in real time, and fixed thresholds cannot adaptively match this time-varying characteristic, leading to frequent false alarms or missed alarms under extreme weather or low-load conditions. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a method, apparatus, electronic device and storage medium for diagnosing faults in heat exchange stations, so as to improve the accuracy of fault diagnosis in heat exchange stations.

[0004] Firstly, a method for diagnosing faults in a heat exchange station is provided, including: Obtain real-time operating parameters and environmental parameters of the heat exchange station; environmental parameters include real-time outdoor ambient temperature and real-time heating load. Based on the real-time outdoor ambient temperature and real-time heating load, the preset rated operating parameters of the heat exchange station are dynamically corrected to obtain the dynamic benchmark threshold corresponding to each real-time operating parameter. The preset fault characteristic values ​​in multiple dimensions are determined based on the degree of deviation between real-time operating parameters and corresponding dynamic benchmark thresholds. Based on the determined fault feature values ​​of multiple dimensions and the preset mapping relationship between fault features and fault sources, the target fault source is determined.

[0005] Optionally, the preset rated operating parameters of the heat exchange station are dynamically corrected based on the real-time outdoor ambient temperature and real-time heating load to obtain the dynamic benchmark thresholds corresponding to each real-time operating parameter, including: The first deviation is determined based on the outdoor ambient temperature and the preset outdoor reference temperature, and the second deviation is determined based on the real-time heating load and the reference load. The first deviation and the second deviation are weighted and fused, and the weighted fusion result is then fused with the basic correction coefficient to obtain the dynamic correction coefficient.

[0006] The preset rated operating parameters are corrected using dynamic correction coefficients to obtain the dynamic benchmark thresholds corresponding to each real-time operating parameter.

[0007] Optionally, the preset rated operating parameters include the rated values ​​of the secondary network supply water temperature, the rated value of the secondary network return water pressure, the rated value of the secondary network supply and return water temperature difference, the rated value of the secondary network supply and return water pressure difference, the rated value of the secondary network flow rate, and the rated operating frequency of the circulating pump; the real-time operating parameters include the secondary network supply water temperature, return water temperature, supply water pressure, return water pressure, real-time flow rate, and the real-time operating frequency of the circulating pump; the preset rated operating parameters are corrected using dynamic correction coefficients to obtain the dynamic reference thresholds corresponding to each real-time operating parameter, including: The preset rated operating parameters are combined with the dynamic correction coefficients to obtain the dynamic reference thresholds for the secondary network water supply temperature, the secondary network return water pressure, the secondary network supply and return water temperature difference, the secondary network supply and return water pressure difference, the secondary network flow rate, and the circulating pump dynamic reference frequency. The dynamic reference threshold for the return water temperature of the secondary network is determined based on the difference between the dynamic reference threshold for the supply water temperature of the secondary network and the dynamic reference threshold for the temperature difference between the supply and return water of the secondary network. The dynamic reference threshold for secondary network water supply pressure is determined based on the sum of the dynamic reference threshold for the return water pressure of the secondary network and the dynamic reference threshold for the pressure difference between the supply and return water of the secondary network.

[0008] Optionally, the preset fault characteristic values ​​in multiple dimensions are determined based on the deviation between real-time operating parameters and corresponding dynamic benchmark thresholds, including: The temperature difference dimension fault characteristic value is determined based on the deviation between the real-time supply and return water temperature difference of the secondary network and the dynamic benchmark threshold of the supply and return water temperature difference of the secondary network. The fault characteristic value of the pressure difference dimension is determined based on the deviation between the real-time supply and return water pressure difference of the secondary network and the dynamic benchmark threshold of the supply and return water pressure difference of the secondary network. The fault characteristic value of the traffic dimension is determined based on the deviation between the real-time traffic of the secondary network and the dynamic benchmark threshold of the secondary network traffic. The pump frequency dimension fault characteristic value is determined based on the deviation between the real-time operating frequency of the circulating pump and the dynamic reference frequency of the circulating pump. The fault characteristic value of heat exchange efficiency is determined based on the real-time temperature difference between the supply and return water temperatures of the secondary network and the input heat power of the primary network.

[0009] Optionally, based on determined fault feature values ​​across multiple dimensions and a predefined mapping relationship between fault features and fault sources, the target fault source is determined as follows: The fault feature values ​​of each dimension are weighted and summed based on the preset weight coefficients of each dimension to obtain the comprehensive fault risk value. When the overall fault risk value exceeds the preset warning threshold, determine the contribution ratio of each dimension of fault characteristic value in the overall fault risk value; Based on the pre-defined mapping relationship between fault features and fault sources, the fault source corresponding to the fault feature of the dimension with the largest contribution is determined as the target fault source.

[0010] Optionally, the method also includes: Based on the dynamic benchmark threshold corresponding to each real-time operating parameter, determine the dynamic safety upper and lower limit thresholds of each real-time operating parameter to match the current operating condition. Based on real-time operating parameters and corresponding dynamic safety upper and lower thresholds, the explicit faults of the heat exchange station are determined.

[0011] Optionally, the method also includes: The overall fault risk value is compared with multiple preset risk threshold intervals to determine the target risk threshold interval to which the overall fault risk value belongs. Based on the preset mapping relationship between risk threshold ranges and warning levels, the target warning level corresponding to the target risk threshold range is determined; Trigger warning actions that match the target's warning level.

[0012] Secondly, a fault diagnosis device for a heat exchange station is provided, comprising: The acquisition unit is used to acquire the real-time operating parameters and environmental parameters of the heat exchange station; the environmental parameters include the real-time outdoor ambient temperature and the real-time heating load. The correction unit is used to dynamically correct the preset rated operating parameters of the heat exchange station based on the real-time outdoor ambient temperature and the real-time heating load, so as to obtain the dynamic reference threshold corresponding to each real-time operating parameter. The first determining unit is used to determine multiple preset fault characteristic values ​​based on the degree of deviation between real-time operating parameters and corresponding dynamic benchmark thresholds. The second determining unit is used to determine the target fault source based on the determined fault feature values ​​of multiple dimensions and the preset mapping relationship between fault features and fault sources.

[0013] Thirdly, an electronic device is provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements any of the methods of the first aspect.

[0014] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when the computer program is executed by a processor, it implements any of the methods of the first aspect.

[0015] This invention provides a method, device, electronic equipment, and storage medium for fault diagnosis of heat exchange stations. It acquires real-time operating parameters and environmental parameters of the heat exchange station; dynamically corrects preset rated operating parameters based on environmental parameters to obtain dynamic benchmark thresholds for each real-time operating parameter; determines preset fault characteristic values ​​across multiple dimensions based on the deviation between real-time operating parameters and corresponding dynamic benchmark thresholds; and identifies the target fault source based on the determined fault characteristic values ​​and the preset mapping relationship between fault characteristics and fault sources. This invention calculates dynamic correction coefficients based on environmental parameters and uses these coefficients to correct rated operating parameters to generate dynamic benchmark thresholds. This allows the fault determination benchmark to adaptively adjust in real-time according to changes in the external environment and internal load, fundamentally solving the problems of high false alarm and high false negative rates in traditional fixed threshold schemes under varying operating conditions, and improving the environmental adaptability and accuracy of fault diagnosis.

[0016] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of a heat exchange station fault diagnosis method provided by an embodiment of the present invention is shown; Figure 2 A flowchart of another heat exchange station fault diagnosis method provided by an embodiment of the present invention is shown; Figure 3 This diagram illustrates the structure of a heat exchange station fault diagnosis device provided in an embodiment of the present invention. Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention is shown. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0020] This invention provides a method for fault diagnosis of heat exchange stations. This method achieves accurate assessment and fault location of the heat exchange station's operating status by constructing a dynamically adaptive diagnostic logic. Specifically, the method includes the following steps: Step S101: Obtain the real-time operating parameters and operating environment parameters of the heat exchange station.

[0021] Specifically, real-time operating parameters such as the water supply temperature of the secondary network Return water temperature Water supply pressure Return water pressure Circulation flow and the real-time operating frequency of the circulating pump These parameters reflect the system's immediate response results.

[0022] It can be controlled by the sampling period These real-time operating parameters are collected periodically.

[0023] To further eliminate transient interference noise from the sensor, in this embodiment, a moving average filtering algorithm is used to preprocess the original data. The filtering formula is as follows:

[0024] In the formula: These are the effective values ​​after parameter filtering. The original running data collected at time i. This represents the number of sliding sampling points. All subsequent calculations will use the filtered, valid data.

[0025] Operating environment parameters refer to external condition variables that affect the heat load demand and operating boundary of the heat exchange station, such as outdoor ambient temperature, real-time heating load index or time period information, etc. These parameters determine the ideal operating state that the system should be in at the current moment.

[0026] Step S102: Based on the operating environment parameters, dynamically correct the preset rated operating parameters of the heat exchange station to obtain the dynamic benchmark threshold corresponding to each real-time operating parameter.

[0027] The rated operating parameters are usually static reference values ​​determined under standard design conditions. However, in actual operation, the optimal operating point of the heat exchange station will drift in real time with the external environment and load demand. Therefore, the dynamic correction in this step is not a simple static lookup and matching, but a real-time adaptive adjustment calculation of the rated operating parameters based on the current operating environment parameters.

[0028] For example, when the outdoor temperature drops, the system automatically raises the baseline threshold for the water supply temperature; when the heating load decreases, the baseline thresholds for flow rate and pressure are lowered accordingly. The dynamic baseline thresholds generated in this way accurately reflect the healthy operating standards that the equipment should meet under current conditions, thus fundamentally solving the problem of frequent false alarms or missed alarms caused by the inability of traditional fixed threshold schemes to adapt to fluctuations in operating conditions.

[0029] Step S103: Determine the preset fault characteristic values ​​in multiple dimensions based on the deviation between the real-time operating parameters and the corresponding dynamic benchmark thresholds.

[0030] Specifically, real-time operating parameters are compared with dynamic benchmark thresholds, and the difference, ratio or other forms of deviation between the two are calculated. These deviations are then mapped to multiple preset dimensions such as temperature difference, pressure difference, flow rate, pump frequency and heat exchange efficiency.

[0031] This feature extraction method based on the degree of deviation can effectively isolate the influence of changes in operating conditions on the absolute value of parameters, making the fault feature value sensitive only to abnormal degradation of equipment performance or sudden failure, thereby significantly improving the ability to identify hidden faults.

[0032] Step S104: Based on the determined fault feature values ​​of multiple dimensions and the preset mapping relationship between fault features and fault sources, determine the target fault source.

[0033] The pre-defined mapping relationship between fault characteristics and fault sources is a logical association rule library pre-built based on the thermodynamic mechanism of heat exchange stations, historical operation and maintenance experience, or machine learning models.

[0034] This mapping relationship describes the specific physical fault type corresponding to a combination of fault characteristics of different dimensions or a significant deviation of a specific characteristic.

[0035] For example, when the characteristic value of the heat exchange efficiency dimension deviates significantly while the temperature difference characteristic is normal, it may be mapped to heat exchanger fouling; when the flow rate and pump frequency characteristics show a specific reverse deviation trend, it may be mapped to circulating pump failure.

[0036] This mapping mechanism can automatically transform abstract multidimensional mathematical features into specific equipment fault locations or types that maintenance personnel can understand, achieving a leap from simple abnormal alarms to precise fault tracing, significantly reducing manual troubleshooting costs and shortening fault response time.

[0037] This embodiment calculates a dynamic correction coefficient based on operating environment parameters and uses this coefficient to correct the rated operating parameters to generate a dynamic benchmark threshold. This allows the benchmark for fault determination to be adaptively adjusted in real time according to changes in the external environment and internal load, fundamentally solving the problems of high false alarm rate and high false alarm rate of traditional fixed threshold schemes under varying operating conditions, and improving the environmental adaptability and accuracy of fault diagnosis.

[0038] Based on the above embodiments, the preset rated operating parameters of the heat exchange station are dynamically corrected based on the operating environment parameters to obtain the dynamic benchmark thresholds corresponding to each real-time operating parameter, including: Step S102A: Determine the first deviation based on the outdoor ambient temperature and the preset outdoor reference temperature, and determine the second deviation based on the real-time heating load and the reference load.

[0039] The first deviation represents the degree of deviation of the current meteorological conditions from the standard design meteorological conditions, reflecting the changing trend of heat loss in the building envelope; the second deviation represents the utilization rate of the current actual heat demand relative to the system design capacity, reflecting the dynamic drift of the hydraulic and thermal operating conditions of the pipeline network.

[0040] Step S102B: Weight the first deviation and the second deviation, and then fuse the weighted result with the basic correction coefficient to obtain the dynamic correction coefficient.

[0041] For example, in a specific computational implementation, the dynamic correction coefficient K can be calculated using the following formula:

[0042] In the formula, To preset the outdoor reference temperature, the local average outdoor temperature during the heating season or the design temperature is usually taken, such as 18℃. Real-time outdoor ambient temperature; The reference load is the design rated heating load of the heat exchange station. For real-time heating load; Temperature-corrected weighting coefficients, The load adjustment weighting factor.

[0043] According to the law of conservation of energy, the instantaneous heat power output of the heat exchange station is equal to the actual heating load of the current pipe network. This value naturally includes the combined effects of building heat storage, pipe network heat loss, and actual user heat consumption, making it the best indicator reflecting true demand. Real-time heating load can be calculated in the following ways:

[0044] in: The specific heat capacity of water, The density of water, This refers to real-time traffic on the secondary network. For the secondary network water supply temperature, This refers to the return water temperature of the secondary network.

[0045] The above dynamic correction coefficient formula eliminates the dimensional differences between different physical quantities through normalization, so that the effects of temperature and load can be superimposed on the same scale.

[0046] In practical engineering applications, and The value of is not fixed, but can be calibrated based on factors such as the building insulation performance and pipeline regulation characteristics of the heat exchange station. As a preferred example, The possible value is 0.4. The value can be 0.3, and the adjustable range for both is generally recommended to be between 0.3 and 0.6 to adapt to the climate characteristics and building types of different regions.

[0047] It should be understood that although the above formula shows the calculation form of linear weighting, in other embodiments, the calculation of dynamic correction coefficients can also be carried out by nonlinear fitting curves, piecewise functions or polynomial regression models, as long as the function of adaptive adjustment of rated parameters based on operating environment parameters can be achieved. This application does not limit this.

[0048] Step S102C: Use dynamic correction coefficients to correct the preset rated operating parameters to obtain the dynamic benchmark thresholds corresponding to each real-time operating parameter.

[0049] In this embodiment, the preset rated operating parameters include the rated value of the secondary network water supply temperature. Rated value of secondary network return water pressure Rated temperature difference between supply and return water in the secondary network Rated pressure difference between supply and return water in the secondary network Secondary network traffic rating and the rated operating frequency of the circulating pump .

[0050] In one feasible implementation, the preset rated operating parameters are corrected using dynamic correction coefficients to obtain the dynamic benchmark thresholds corresponding to each real-time operating parameter, including: Step A: Combine the preset rated operating parameters with the dynamic correction coefficient to obtain the corresponding dynamic reference threshold for the secondary network water supply temperature. Dynamic reference threshold for secondary network return water pressure Dynamic reference threshold for temperature difference between supply and return water in secondary network Dynamic benchmark threshold for pressure difference between supply and return water in secondary network Secondary network traffic dynamic baseline threshold and the dynamic reference frequency of the circulating pump .

[0051] For example, the dynamic benchmark thresholds are represented as follows: 、 、 ; , , .

[0052] Step B: Determine the dynamic reference threshold for the return water temperature of the secondary network based on the difference between the dynamic reference threshold for the supply water temperature of the secondary network and the dynamic reference threshold for the temperature difference between the supply and return water of the secondary network.

[0053] Given the known dynamic reference threshold for secondary network water supply temperature Temperature difference between supply and return water in the secondary network Based on this, the dynamic reference threshold for the secondary network return water temperature was derived. .

[0054] Regarding temperature parameters, return water temperature is essentially a representation of the residual heat energy after the supply water temperature has dissipated through the heat exchanger. Its value is jointly determined by the supply water temperature and the heat dissipation (reflected as a temperature difference). If a correction factor is directly applied to the rated value of return water temperature, the reference may be distorted because the dynamic changes in the supply and return water temperature difference are ignored.

[0055] For example, when the load decreases, the supply water temperature may only need minor adjustments, but the temperature difference will significantly narrow, at which point the return water temperature should drop substantially. If the return water temperature is corrected using only a uniform coefficient, it is very easy to cause the baseline to be too high, leading to missed low-temperature faults. Therefore, the difference method of "supply water baseline minus temperature difference baseline" can strictly follow the law of conservation of energy, ensuring that the generated dynamic baseline threshold for return water temperature is physically consistent with the supply water temperature and heat exchange efficiency.

[0056] Step C: Determine the dynamic reference threshold for the secondary network supply water pressure based on the sum of the dynamic reference threshold for the secondary network return water pressure and the dynamic reference threshold for the pressure difference between the secondary network supply and return water.

[0057] Similarly, for pressure parameters, the supply water pressure is the power source for overcoming the resistance of the pipe network and providing the static pressure of the return water. Its value is equal to the return water pressure plus the friction loss and local resistance loss along the pipe network (reflected as pressure difference). Using the summation method of "return water reference plus pressure difference reference" can accurately reflect the resistance superposition effect in the fluid transportation and distribution process, and avoid severing its intrinsic connection with the hydraulic characteristics of the pipe network by adjusting the supply water pressure alone.

[0058] Therefore, based on the return water pressure, the dynamic reference threshold for the secondary network water supply pressure can be derived as follows: .

[0059] This embodiment allows us to obtain the single-point dynamic benchmark threshold corresponding to each real-time operating parameter.

[0060] Based on the above embodiments, determining preset fault characteristic values ​​in multiple dimensions based on the deviation between real-time operating parameters and corresponding dynamic benchmark thresholds includes: Step S103A: Determine the fault characteristic value of the temperature difference dimension based on the deviation between the real-time supply and return water temperature difference of the secondary network and the dynamic reference threshold of the supply and return water temperature difference of the secondary network.

[0061] The fault characteristic value of the temperature difference dimension can be obtained by calculating the difference or relative deviation rate between the real-time supply and return water temperature difference and the dynamic reference temperature difference. This characteristic value can sensitively detect thermal imbalances caused by abnormal valve opening, sudden load changes, or heat source fluctuations.

[0062] For example, fault characteristic values ​​in the temperature difference dimension ; in, This indicates the real-time temperature difference between the supply and return water in the secondary network.

[0063] Step S103B: Determine the fault characteristic value of the pressure difference dimension based on the deviation between the real-time supply and return water pressure difference of the secondary network and the dynamic benchmark threshold of the supply and return water pressure difference of the secondary network.

[0064] The differential pressure dimension fault characteristic value characterizes the changes in pipeline resistance and is a key indicator for identifying filter blockage or pipeline leakage.

[0065] For example, differential pressure dimension fault characteristic values

[0066] in, This indicates the real-time supply and return water pressure difference in the secondary network.

[0067] Step S103C: Determine the fault characteristic value of the traffic dimension based on the deviation between the real-time traffic of the secondary network and the dynamic benchmark threshold of the secondary network traffic.

[0068] For example, traffic dimension fault characteristic values .

[0069] Step S103D: Determine the pump frequency dimension fault characteristic value based on the deviation between the real-time operating frequency of the circulating pump and the dynamic reference frequency of the circulating pump.

[0070] For example, pump frequency dimension fault characteristic value .

[0071] The fault characteristic values ​​of flow rate and pump frequency together constitute the state profile of the hydraulic transmission and distribution system, which is used to monitor the operating efficiency of circulating pumps and the hydraulic balance of the pipeline network.

[0072] Temperature difference, pressure difference, flow rate, and pump frequency are four dimensions that are explicit deviation characteristics. They directly reflect the instantaneous deviation of the key operating parameters of the heat exchange station from the ideal benchmark under the current operating conditions.

[0073] Step S103E: Determine the fault characteristic value of heat exchange efficiency dimension based on the real-time temperature difference between the supply and return water temperatures of the secondary network and the input heat power of the primary network.

[0074] Unlike the explicit characteristics mentioned above, the fault characteristic value of the heat exchange efficiency dimension is an implicit performance characteristic. It is not directly manifested as the exceeding of a single parameter, but rather comprehensively reflects whether the heat transfer capacity of the heat exchanger body has been reduced.

[0075] Under ideal conditions with complete data, heat transfer efficiency can be accurately calculated using thermodynamic formulas. For example, the heat transfer efficiency η can be expressed as the ratio of heat absorbed by the secondary network to heat input to the primary network, and the calculation formula is as follows:

[0076] In the formula, The specific heat capacity of water, The density of water, This refers to real-time traffic on the secondary network. For the secondary network water supply temperature, This refers to the return water temperature of the secondary network. This is the input thermal power to the primary network.

[0077] Heat exchange efficiency dimension fault characteristic value .

[0078] This formula, based on the law of conservation of energy, can accurately quantify the actual working efficiency of a heat exchanger. However, in practical engineering applications, high-precision heat meters are often not installed on the primary network side, or data transmission from the heat meters may experience delays, losses, or even damage, leading to… Data is often missing or unreliable. If only the standard formulas mentioned above are relied upon, the entire fault diagnosis system will fail or produce misjudgments once the primary network data is abnormal, due to the lack of a key efficiency dimension.

[0079] To address this technical challenge, this embodiment introduces a substitute characterization mechanism for heat exchange efficiency. When primary network input heat power data is missing or unreliable, the product of the secondary network supply and return water temperature difference and the real-time flow rate is used as a substitute characterization parameter for the heat exchange efficiency dimension of the fault characteristic value. From a thermodynamic perspective, the actual heating load on the secondary network side... .

[0080] During a continuous operating cycle at the same heat exchange station, the specific heat capacity of water... and density It can be considered a constant, therefore the heating load and They exhibit a strictly linear proportional relationship.

[0081] While this product cannot provide an absolute percentage of efficiency, it accurately characterizes the relative heat exchanger performance trend at the current flow rate. When the heat exchanger becomes fouled or clogged, the supply and return water temperature difference will decrease significantly even if the flow rate remains constant, causing the product value to decrease; conversely, if the heat exchanger performance recovers after cleaning, the product value will increase.

[0082] Therefore, using it as a fault characteristic value can fully meet the diagnostic needs of identifying heat exchanger performance degradation.

[0083] This embodiment effectively solves the diagnostic blind spot problem caused by incomplete sensor configuration or poor data quality, and greatly improves the adaptability and robustness of the technical solution under different hardware conditions.

[0084] Based on the above embodiments, and based on the determined fault feature values ​​of multiple dimensions and the preset mapping relationship between fault features and fault sources, the target fault source is determined to include: Step S104A: Based on the preset weight coefficients for each dimension, the fault feature values ​​of each dimension are weighted and summed to obtain the comprehensive fault risk value.

[0085] Specifically, the overall failure risk value S can be calculated using the following formula:

[0086] In the formula, , , , , These represent fault characteristic values ​​(all normalized) for the dimensions of temperature difference, pressure difference, flow rate, heat exchange efficiency, and pump frequency, respectively. , , , , These are the weight coefficients for the corresponding dimensions, and they satisfy... .

[0087] The weighting coefficients reflect the varying degrees of harm that different parameter anomalies pose to the overall safety of the heat exchange station. For example, in a preferred configuration, considering that thermal imbalance and pressure anomalies are often direct causes of safety accidents, the temperature difference weighting can be adjusted. and pressure difference weight All values ​​are set to 0.25; flow rate and heat exchange efficiency As a performance indicator, the weight can be set to 0.2; pump frequency As an indicator of equipment status, the weight can be set to 0.1.

[0088] It should be understood that the above weights are merely exemplary values. In practical applications, maintenance personnel can dynamically adjust them based on the aging of the heat exchange station's equipment, the pipeline topology, and the distribution of historical faults.

[0089] For example, for aging pipeline systems, the weight of differential pressure can be appropriately increased to enhance sensitivity to leakage risks; for newly commissioned heat exchangers, the weight of heat exchange efficiency can be appropriately increased to monitor installation quality or initial scaling trends. Through this weighted summation mechanism, the system compresses scattered multidimensional anomaly information into a scalar S value between 0 and 1. The larger the value, the higher the overall risk of the system, thus providing a unified quantitative basis for subsequent graded early warning.

[0090] Step S104B: When the overall fault risk value exceeds the preset warning threshold, determine the contribution ratio of each dimension of fault characteristic value in the overall fault risk value.

[0091] Furthermore, when the overall fault risk value S exceeds the preset warning threshold (e.g., 0.2), the system not only triggers a warning, but also automatically analyzes the components of the risk, that is, determines the contribution ratio of each dimension of fault characteristic value in the overall fault risk value.

[0092] Contribution percentage of a certain dimension of fault characteristics The calculation formula is:

[0093] This contribution percentage Essentially, it represents the "energy share" or "dominance" of anomalies in each dimension within the current comprehensive failure risk.

[0094] Unlike simple parameter over-limit alarms, contribution ratio analysis can isolate background noise caused by operating condition fluctuations and accurately identify the core driving factors that cause the system to deviate from its healthy state. For example, even if both temperature difference and flow rate show slight deviations, if the contribution ratio of the temperature difference dimension is as high as 70%, it indicates that the current risk is mainly caused by thermal imbalance, rather than hydraulic distribution problems.

[0095] Step S104C: Based on the preset mapping relationship between fault features and fault sources, the fault source corresponding to the fault feature of the dimension with the largest contribution ratio is determined as the target fault source.

[0096] The following are some typical mapping rules and their underlying physical mechanisms: In the first scenario, if the contribution of the fault characteristic value in the heat exchange efficiency dimension is the highest, then the target fault source is determined to be heat exchanger scaling or blockage.

[0097] This is because heat exchange efficiency is an indicator that directly characterizes the heat transfer performance of the heat exchanger body. When scale forms on the plate surface or the flow channel is blocked, the heat transfer resistance increases significantly, resulting in a decrease in heat exchange under the same temperature difference and flow rate. This leads to an abnormal increase in the characteristic value of the efficiency dimension, while other hydraulic parameters may still be within the normal range.

[0098] In the second scenario, if the sum of the contribution ratios of the fault characteristic values ​​in the flow rate dimension and the fault characteristic values ​​in the pump frequency dimension is the highest, and the two show an opposite deviation trend (for example, the pump frequency increases but the flow rate decreases, or the pump frequency is normal but the flow rate decreases abnormally), then the target fault source is determined to be a circulating water pump fault.

[0099] This combined judgment logic utilizes the performance curve characteristics of the pump: when the pump experiences impeller wear, cavitation, or inlet filter blockage, its work capacity decreases, manifesting as an inability to provide the rated flow rate at the same or higher frequencies. A low flow rate alone might indicate a small valve opening, and a high pump frequency alone might indicate a high load demand. However, when these two factors are inversely coupled and jointly dominate the risk value, it strongly points to a mechanical failure in the pump itself.

[0100] In the third scenario, if the contribution of the differential pressure dimension fault characteristic value is the highest, then the target fault source is determined to be pipeline blockage or leakage.

[0101] The differential pressure directly reflects the resistance characteristics of the secondary network system. A significant contribution indicates a drastic change in system resistance. An abnormally large differential pressure usually corresponds to filter blockage or foreign object blockage in the pipeline; an abnormally small differential pressure may indicate a leak in the pipeline network leading to pressure release.

[0102] In the fourth scenario, if the contribution of the fault characteristic value in the temperature difference dimension is the highest, then the target fault source is determined to be a malfunctioning temperature control valve or a fluctuation in the primary network heat source.

[0103] Temperature difference is a direct reflection of the balance between heat supply and demand. After ruling out problems with the heat exchanger itself, significant deviations in temperature difference often stem from the failure of the regulating actuator (such as jamming of the electric regulating valve or drift of the controller's PID parameters) or large fluctuations in the upstream primary water supply temperature.

[0104] It should be noted that the above mapping relationship is not limited to a fixed rule base or threshold comparison. In other embodiments, the mapping relationship can also be constructed using machine learning models such as decision trees, random forests, support vector machines, or neural networks.

[0105] For example, sample data labeled with actual fault types from historical operation and maintenance records can be used as a training set, allowing the model to automatically learn the nonlinear mapping relationship between multi-dimensional contribution ratio combinations and fault sources, thereby improving the diagnostic accuracy of complex concurrent faults. In addition, the judgment logic of "maximum contribution ratio" is not limited to a single dimension, but can also support multi-dimensional combination judgment (such as the aforementioned water pump fault judgment), as long as the combination pattern is defined as the feature fingerprint of a specific fault source in the preset mapping relationship.

[0106] Based on the above embodiments, such as Figure 2 As shown, the method also includes: Step S105: Determine the dynamic safety upper and lower limit thresholds of each real-time operating parameter that match the current operating condition based on the dynamic benchmark threshold corresponding to each real-time operating parameter. Step S106: Based on real-time operating parameters and corresponding dynamic safety upper and lower limit thresholds, determine the explicit faults of the heat exchange station.

[0107] The dynamic benchmark threshold mentioned in the previous embodiments is mainly used to measure the degree of deviation of equipment performance from ideal operating conditions, and belongs to the optimal operating reference line; while the dynamic safety upper and lower limit thresholds in this step are absolute safety red lines generated in real time based on the benchmark threshold. For example, the range of ±10% of the dynamic benchmark threshold can be set as the dynamic safety upper limit threshold and the dynamic safety lower limit threshold, respectively.

[0108] For example, dynamic safety upper and lower thresholds are represented as follows:

[0109] For example, if the dynamic baseline threshold for the secondary network water supply temperature is 55℃ at a certain moment, then its dynamic safety upper limit threshold is 60.5℃ and its dynamic safety lower limit threshold is 49.5℃.

[0110] When the real-time operating parameters exceed this dynamic envelope range, regardless of whether the comprehensive fault risk value S reaches the warning threshold, it is directly judged as an explicit fault.

[0111] This design constitutes a hard boundary protection mechanism independent of the multidimensional risk quantification model, specifically designed to detect sudden and catastrophic anomalies caused by sensor drift, actuator jamming, or pipeline rupture. Because the safety boundary itself dynamically adjusts with operating conditions, this mechanism avoids false alarms caused by excessively low fixed upper limits during high-load winter operation and prevents missed alarms caused by excessively high fixed lower limits during low-load summer operation, ensuring all-weather adaptability for identifying explicit faults.

[0112] Based on the above embodiments, the method further includes: Step S104D: Compare the comprehensive fault risk value with multiple preset risk threshold intervals to determine the target risk threshold interval to which the comprehensive fault risk value belongs.

[0113] For example, the preset risk threshold ranges are [0,0.2), [0.2,0.5), and [0.5,1.0].

[0114] Step S104E: Based on the preset mapping relationship between risk threshold ranges and warning levels, determine the target warning level corresponding to the target risk threshold range.

[0115] The specific classification is as follows: When the comprehensive fault risk value S is in the range of [0, 0.2), it is judged as a Level 1 normal state. When S is in the range of [0.2, 0.5), it is judged as a Level 2 minor warning. When S is in the range of [0.5, 1.0], it is judged as a Level 3 emergency warning.

[0116] Step S104F: Trigger a warning action that matches the target warning level.

[0117] When the system is determined to be in a Level 1 normal state, it only records background data and does not trigger any active alarms to avoid unnecessary interference to maintenance personnel. When the system is determined to be in a Level 2 minor warning state, it usually corresponds to hidden performance degradation faults such as initial scaling of heat exchangers and valve adjustment lag. At this time, the system triggers SMS or APP push notifications to remind maintenance personnel to pay close attention or arrange preventive maintenance during the next inspection. When the system is determined to be in a Level 3 emergency warning state, it indicates that there is a serious risk of thermal imbalance or equipment failure in the system. At this time, the system immediately triggers on-site audible and visual alarms and sends a high-priority work order to the management platform, requiring maintenance personnel to intervene and handle the situation immediately.

[0118] This embodiment transforms abstract risk values ​​into operational and maintenance instructions with clear action orientation through this differentiated hierarchical response strategy. This effectively solves the operational and maintenance fatigue problem caused by the "reporting every alarm" approach in traditional solutions, allowing limited operational and maintenance resources to be prioritized for handling high-risk faults, and significantly improving the safety management level of heat exchange stations.

[0119] Based on the same inventive concept, a heat exchange station fault diagnosis device is provided, such as... Figure 3 As shown, it includes: The acquisition unit 301 is used to acquire the real-time operating parameters and operating environment parameters of the heat exchange station; the operating environment parameters include the real-time outdoor ambient temperature and the real-time heating load. The correction unit 302 is used to dynamically correct the preset rated operating parameters of the heat exchange station based on the real-time outdoor ambient temperature and the real-time heating load, so as to obtain the dynamic reference threshold corresponding to each real-time operating parameter. The first determining unit 303 is used to determine multiple preset fault feature values ​​based on the degree of deviation between real-time operating parameters and corresponding dynamic benchmark thresholds. The second determining unit 304 is used to determine the target fault source based on the determined fault feature values ​​of multiple dimensions and the preset mapping relationship between fault features and fault sources.

[0120] Based on the same technical concept, embodiments of the present invention also provide an electronic device, such as... Figure 4 As shown, it includes a processor 401, a communication interface 402, a memory 403, and a communication bus 404, wherein the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404.

[0121] Memory 403 is used to store computer programs; When the processor 401 executes the program stored in the memory 403, it implements the steps of the above method embodiment.

[0122] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0123] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0124] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0125] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0126] The computer program product for diagnosing heat exchange station faults provided in this embodiment of the invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0127] The heat exchange station fault diagnosis device provided in this embodiment of the invention can be specific hardware on the equipment or software or firmware installed on the equipment. The implementation principle and technical effects of the device provided in this embodiment of the invention are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiments can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0128] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0129] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] In addition, the functional units in the embodiments provided by the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0131] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0132] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0133] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. All should be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for diagnosing faults in a heat exchange station, characterized in that, include: The real-time operating parameters and environmental parameters of the heat exchange station are obtained; the environmental parameters include the real-time outdoor ambient temperature and the real-time heating load. Based on the real-time outdoor ambient temperature and real-time heating load, the preset rated operating parameters of the heat exchange station are dynamically corrected to obtain the dynamic benchmark threshold corresponding to each real-time operating parameter. Based on the degree of deviation between the real-time operating parameters and the corresponding dynamic benchmark threshold, preset fault characteristic values ​​in multiple dimensions are determined. Based on the determined fault feature values ​​of multiple dimensions and the preset mapping relationship between fault features and fault sources, the target fault source is determined.

2. The method according to claim 1, characterized in that, The dynamic correction of the preset rated operating parameters of the heat exchange station based on the real-time outdoor ambient temperature and real-time heating load to obtain the dynamic benchmark thresholds corresponding to each real-time operating parameter includes: Based on the outdoor ambient temperature and the preset outdoor reference temperature, a first deviation is determined, and based on the real-time heating load and the reference load, a second deviation is determined. The first deviation and the second deviation are weighted and fused, and the weighted fusion result is then fused with the basic correction coefficient to obtain the dynamic correction coefficient. The preset rated operating parameters are corrected using the dynamic correction coefficient to obtain the dynamic benchmark threshold corresponding to each real-time operating parameter.

3. The method according to claim 2, characterized in that, The preset rated operating parameters include the rated value of the secondary network supply water temperature, the rated value of the secondary network return water pressure, the rated value of the secondary network supply and return water temperature difference, the rated value of the secondary network supply and return water pressure difference, the rated value of the secondary network flow rate, and the rated operating frequency of the circulating pump; the real-time operating parameters include the secondary network supply water temperature, return water temperature, supply water pressure, return water pressure, real-time flow rate, and real-time operating frequency of the circulating pump. The step of using the dynamic correction coefficient to correct the preset rated operating parameters to obtain the dynamic benchmark threshold corresponding to each real-time operating parameter includes: The preset rated operating parameters are respectively integrated with the dynamic correction coefficient to obtain the dynamic reference threshold of the secondary network water supply temperature, the dynamic reference threshold of the secondary network return water pressure, the dynamic reference threshold of the secondary network supply and return water temperature difference, the dynamic reference threshold of the secondary network supply and return water pressure difference, the dynamic reference threshold of the secondary network flow rate, and the dynamic reference frequency of the circulating pump. The dynamic reference threshold for the return water temperature of the secondary network is determined based on the difference between the dynamic reference threshold for the secondary network supply water temperature and the dynamic reference threshold for the temperature difference between the secondary network supply and return water. The dynamic reference threshold for secondary network water supply pressure is determined based on the sum of the dynamic reference threshold for the return water pressure of the secondary network and the dynamic reference threshold for the pressure difference between the supply and return water of the secondary network.

4. The method according to claim 3, characterized in that, The determination of preset fault feature values ​​across multiple dimensions based on the deviation between the real-time operating parameters and the corresponding dynamic benchmark threshold includes: The temperature difference dimension fault characteristic value is determined based on the deviation between the real-time supply and return water temperature difference of the secondary network and the dynamic benchmark threshold of the supply and return water temperature difference of the secondary network. The fault characteristic value of the pressure difference dimension is determined based on the deviation between the real-time supply and return water pressure difference of the secondary network and the dynamic benchmark threshold of the supply and return water pressure difference of the secondary network. The fault characteristic value of the traffic dimension is determined based on the deviation between the real-time traffic of the secondary network and the dynamic benchmark threshold of the secondary network traffic. The pump frequency dimension fault characteristic value is determined based on the deviation between the real-time operating frequency of the circulating pump and the dynamic reference frequency of the circulating pump. The fault characteristic value of heat exchange efficiency is determined based on the real-time temperature difference between the supply and return water temperatures of the secondary network and the input heat power of the primary network.

5. The method according to claim 4, characterized in that, The determination of the target fault source based on determined fault feature values ​​of multiple dimensions and a preset mapping relationship between fault features and fault sources includes: The fault feature values ​​of each dimension are weighted and summed based on the preset weight coefficients of each dimension to obtain the comprehensive fault risk value. When the overall fault risk value exceeds the preset warning threshold, the contribution ratio of each dimension of fault feature value to the overall fault risk value is determined. Based on the pre-defined mapping relationship between fault features and fault sources, the fault source corresponding to the fault feature of the dimension with the largest contribution is determined as the target fault source.

6. The method according to claim 4, characterized in that, The method further includes: Based on the dynamic benchmark threshold corresponding to each real-time operating parameter, determine the dynamic safety upper and lower limit thresholds of each real-time operating parameter to match the current operating condition. Based on the real-time operating parameters and the corresponding dynamic safety upper and lower limit thresholds, the explicit faults of the heat exchange station are determined.

7. The method according to claim 5, characterized in that, The method further includes: The comprehensive fault risk value is compared with multiple preset risk threshold intervals to determine the target risk threshold interval to which the comprehensive fault risk value belongs. Based on the preset mapping relationship between risk threshold ranges and warning levels, the target warning level corresponding to the target risk threshold range is determined; Trigger a warning action that matches the warning level of the target.

8. A fault diagnosis device for a heat exchange station, characterized in that, include: The acquisition unit is used to acquire the real-time operating parameters and environmental parameters of the heat exchange station; the environmental parameters include the real-time outdoor ambient temperature and the real-time heating load. The correction unit is used to dynamically correct the preset rated operating parameters of the heat exchange station based on the real-time outdoor ambient temperature and real-time heating load, so as to obtain the dynamic benchmark threshold corresponding to each real-time operating parameter. The first determining unit is used to determine multiple preset fault feature values ​​based on the degree of deviation between the real-time operating parameters and the corresponding dynamic benchmark threshold. The second determining unit is used to determine the target fault source based on the determined fault feature values ​​of multiple dimensions and the preset mapping relationship between fault features and fault sources.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used to store computer programs; When the processor executes the program stored in the memory, it implements the method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images