Unattended heat exchange station monitoring system and control method thereof

Abstract

The invention discloses an unattended heat exchange station monitoring system and a control method thereof, and the system comprises a setting module which is used for determining a plurality of demand modules of a heat exchange station, and setting concerned equipment according to the influence degree of heat exchange station equipment on the demand modules; the monitoring module is used for presetting a plurality of feature monitoring indexes, setting a plurality of monitoring points of each concerned device based on the feature monitoring indexes, acquiring real-time monitoring data of the corresponding concerned devices, and generating monitoring evaluation values of the feature monitoring indexes corresponding to the concerned devices according to the real-time monitoring data; and the display module is used for constructing a correlation model according to all the monitoring points, determining the real-time state of the heat exchange station according to the correlation model and all the monitoring evaluation values, and sending the real-time state to the monitoring terminal for display, so that the unattended monitoring efficiency and monitoring accuracy of the heat exchange station are improved, and safe and efficient operation of the heat exchange station is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of heat exchange station monitoring, and in particular to an unmanned heat exchange station monitoring system and a control method thereof. Background Art

[0002] The heat exchange station is an important part of the urban heating system. Its safe, stable and efficient operation is crucial to ensuring the heating and life of residents. Heat exchange station monitoring is an important means to ensure its safe, stable and efficient operation.

[0003] In the prior art, the heat exchange station is monitored by relying on manual inspection or traditional monitoring system. However, the heat exchange station involves a large number of equipment, manual inspection is time-consuming and labor-intensive, and equipment failures cannot be discovered in a timely manner. The traditional monitoring system does not comprehensively analyze the monitoring data of the equipment and cannot accurately judge the operating status of the heat exchange station, resulting in low heating efficiency of the heat exchange station and energy waste. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides an unmanned heat exchange station monitoring system and a control method thereof. By setting multiple focus devices and setting monitoring points of the focus devices based on characteristic monitoring indicators, real-time monitoring data is obtained and monitoring evaluation values ​​are generated. An association model is constructed according to the monitoring points, and the real-time status of the heat exchange station is determined according to the association model and the monitoring evaluation values, thereby improving the unmanned monitoring efficiency and monitoring accuracy of the heat exchange station and ensuring the safe and efficient operation of the heat exchange station.

[0005] In some embodiments of the present application, an unattended heat exchange station monitoring system is provided, comprising:

[0006] A setting module is used to determine multiple demand modules of the heat exchange station and set the focus equipment according to the influence of the heat exchange station equipment on the demand modules;

[0007] A monitoring module is used to pre-set multiple characteristic monitoring indicators, set multiple monitoring points for each device of interest based on the characteristic monitoring indicators, obtain real-time monitoring data of the corresponding device of interest, and generate a monitoring evaluation value of the characteristic monitoring indicator corresponding to the device of interest based on the real-time monitoring data;

[0008] The display module is used to build an association model based on all monitoring points, determine the real-time status of the heat exchange station based on the association model and all monitoring evaluation values, and send the real-time status to the monitoring terminal for display.

[0009] In some embodiments of the present application, the focus device is set according to the influence of the heat exchange station device on the demand module, including:

[0010] Obtaining specific uses and demand instructions of heat exchange station equipment, determining the functional type of the corresponding heat exchange station equipment according to the specific uses and demand instructions, dividing the heat exchange station equipment of the same functional type into the same demand module, and obtaining multiple demand modules and corresponding heat exchange station equipment;

[0011] Determine multiple operation processes corresponding to the demand module according to the demand instructions of each demand module, and divide the operation processes into main operation processes and secondary operation processes;

[0012] Obtain the first application coefficient and the first important coefficient of the heat exchange station equipment in each demand module for the main operation process and the second application coefficient and the second important coefficient of the secondary operation process;

[0013] Generate a first influence coefficient according to the number of main operation processes whose first application coefficient is greater than the first preset application coefficient, the first application coefficient difference value greater than the first preset application coefficient, the number of main operation processes whose first importance coefficient is greater than the first preset importance coefficient, and the first importance coefficient difference value greater than the first preset importance coefficient;

[0014] Generate a second influence coefficient according to the number of secondary operation processes whose second application coefficient is greater than the second preset application coefficient, the second application coefficient difference value greater than the second preset application coefficient, the number of secondary operation processes whose second importance coefficient is greater than the second preset importance coefficient, and the second importance coefficient difference value greater than the second preset importance coefficient;

[0015] The influence degree of the heat exchange station equipment on the corresponding demand module is generated according to the first influence coefficient and the second influence coefficient.

[0016] In some embodiments of the present application, the calculation formula of the influence degree is:

[0017]

[0018]

[0019] Wherein, Y is the influence degree, c1 is the weight coefficient of the first influence coefficient, m1 is the number of main operation processes whose first application coefficient is greater than the first preset application coefficient, n1 is the total number of main operation processes, △y1i is the ith first application coefficient difference, a1 is the weight coefficient of the first application coefficient, m2 is the number of main operation processes whose first important coefficient is greater than the first preset important coefficient, △z1s is the sth first important coefficient difference, is the first influence coefficient, u1 is the number of secondary operation processes whose second application coefficient is greater than the second preset application coefficient, n2 is the total number of secondary operation processes, △y2r is the rth second application coefficient difference, a2 is the weight coefficient of the second application coefficient, u2 is the number of secondary operation processes whose second important coefficient is greater than the second preset important coefficient, △z2v is the vth second important coefficient difference, b2 is the weight coefficient of the second important coefficient, is the second influence coefficient.

[0020] In some embodiments of the present application, generating a monitoring evaluation value of a characteristic monitoring indicator corresponding to a device of interest according to monitoring-related data includes:

[0021] Preset multiple characteristic monitoring indicators, set monitoring points corresponding to the concerned equipment according to the correlation between the characteristic monitoring indicators and the historical monitoring data of the concerned equipment, configure different sensors for the monitoring points, and set the collection time nodes of the corresponding sensors according to the fluctuation degree of the historical monitoring data corresponding to the multiple sensors at the monitoring points;

[0022] Acquire multiple real-time monitoring data of the monitoring point of the device of interest at the current acquisition time node, compare the real-time monitoring data of the same characteristic monitoring indicator of the current device of interest with the corresponding standard monitoring data, and generate a first evaluation value of the corresponding characteristic monitoring indicator according to the comparison result;

[0023] The real-time monitoring data of the same characteristic monitoring indicator of the focus device at the current acquisition time node is compared with the historical monitoring data corresponding to the previous acquisition time node to obtain multiple fluctuation values, and a compensation coefficient is generated according to the multiple fluctuation values. The first evaluation value is corrected according to the compensation coefficient to obtain the monitoring evaluation value of the corresponding characteristic monitoring indicator of the focus device.

[0024]

[0025] Where J is the monitoring evaluation value, w is the total number of real-time monitoring data corresponding to the characteristic monitoring index of the equipment of interest, hd is the weight coefficient of the d-th real-time monitoring data, gd is the d-th real-time monitoring data, g′d is the d-th standard monitoring data, is the compensation coefficient, p is the compensation conversion coefficient, ld is the fluctuation value of the d-th real-time monitoring data, and l′d is the d-th standard fluctuation value.

[0026] In some embodiments of the present application, a correlation model is constructed based on all monitoring points, including:

[0027] Obtain the historical operation log of each monitoring point, analyze the historical operation log, and filter out the historical fault data and historical normal data of the corresponding monitoring point;

[0028] The historical fault data of each monitoring point is used to determine the triggering of the monitoring point, determine the monitoring point that is triggered in the preset period and obtain the corresponding historical fault data, and use the historical fault data of the current monitoring point as the first training input data set, and the triggered monitoring point and the corresponding historical fault data as the training output label set;

[0029] The historical normal data of each monitoring point is used as a second training input data set, and the monitoring points that have not been triggered within a preset period of time and the corresponding historical normal data are used as a training output unlabeled set;

[0030] Based on the first training input data set, the training output labeled set, the second training input data set and the training output unlabeled set, semi-supervised learning training is performed to generate an association model.

[0031] In some embodiments of the present application, the real-time status of the heat exchange station is determined according to the correlation model and all monitoring evaluation values, including:

[0032] Obtain the real-time monitoring data of each monitoring point of the equipment of interest, and determine whether the monitoring point has a fault based on the comparison result between the real-time monitoring data and the corresponding standard monitoring data. If so, filter out the faulty monitoring point and obtain the real-time fault data;

[0033] Input the fault monitoring points and real-time fault data into the correlation model, obtain all triggered monitoring points and corresponding real-time fault data, and construct a fault monitoring data set;

[0034] Generate a first state coefficient based on the weight coefficient of the concerned device corresponding to each monitoring point in the fault monitoring data set and the fault degree of the real-time fault data;

[0035] Comprehensively analyze the monitoring evaluation values ​​of the same characteristic monitoring indicators of multiple concerned equipment to obtain the comprehensive monitoring evaluation values ​​of the corresponding characteristic monitoring indicators of the heat exchange station;

[0036] Generate a second state coefficient according to the comprehensive monitoring evaluation values ​​of the multiple characteristic monitoring indicators and the weight coefficients of the corresponding characteristic monitoring indicators;

[0037] Generate a comprehensive state coefficient of the current acquisition time node of the heat exchange station according to the first state coefficient and the second state coefficient;

[0038] Presetting a state coefficient threshold;

[0039] When the comprehensive state coefficient is greater than the state coefficient threshold, the real-time state of the heat exchange station is determined to be a healthy state;

[0040] When the comprehensive state coefficient is less than the state coefficient threshold, the state coefficient difference between the comprehensive state coefficient and the state coefficient threshold is calculated, and the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is determined according to the relationship between the state coefficient difference and the preset state coefficient difference, and the adjustment instruction of the heat exchange station is generated according to the abnormal probability.

[0041] In some embodiments of the present application, a first preset state coefficient difference interval, a second preset state coefficient difference interval, a third preset state coefficient difference interval and a fourth preset state coefficient difference interval are preset;

[0042] When the state coefficient difference is within the first preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is the first preset abnormal probability;

[0043] When the state coefficient difference is in the second preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is the second preset abnormal probability;

[0044] When the state coefficient difference is in the third preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is the third preset abnormal probability;

[0045] When the state coefficient difference is in the fourth preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current collection time node and the next collection time node is the fourth preset abnormal probability.

[0046] In some embodiments of the present application, generating a regulation instruction for a heat exchange station according to the abnormal probability includes:

[0047] When the abnormal probability is less than or equal to the second preset abnormal probability, a first-level adjustment instruction is generated, wherein the first-level adjustment instruction includes predicting the hidden fault characteristics of the heat exchange station within the time interval between the current acquisition time node and the next acquisition time node;

[0048] When the abnormal probability is between the second preset abnormal probability and the third preset abnormal probability, a secondary adjustment instruction is generated, wherein the secondary adjustment indicator includes determining the hidden fault characteristics of the heat exchange station at the current acquisition time node and configuring a corresponding adjustment strategy for the hidden fault characteristics;

[0049] When the abnormal probability is greater than the third preset abnormal probability, a third adjustment instruction is generated, wherein the third adjustment instruction includes determining the dominant fault feature of the heat exchange station at the current acquisition time node and configuring a corresponding adjustment strategy for the dominant fault feature.

[0050] In some embodiments of the present application, a control method for an unattended heat exchange station monitoring system is also included:

[0051] Determine multiple demand modules of the heat exchange station, and set the focus equipment according to the influence of the heat exchange station equipment on the demand modules;

[0052] Preset multiple characteristic monitoring indicators, set multiple monitoring points for each device of interest based on the characteristic monitoring indicators, obtain real-time monitoring data of the corresponding device of interest, and generate monitoring evaluation values ​​of the characteristic monitoring indicators corresponding to the device of interest based on the real-time monitoring data;

[0053] A correlation model is constructed based on all monitoring points, and the real-time status of the heat exchange station is determined based on the correlation model and all monitoring evaluation values, and the real-time status is sent to the monitoring terminal for display.

[0054] Compared with the prior art, the unattended heat exchange station monitoring system and control method of the embodiment of the present application have the following beneficial effects:

[0055] By setting multiple devices of interest and setting monitoring points of the devices of interest based on characteristic monitoring indicators, real-time monitoring data is obtained and monitoring evaluation values ​​are generated. A correlation model is built according to the monitoring points, and the real-time status of the heat exchange station is determined according to the correlation model and the monitoring evaluation values. This improves the unmanned monitoring efficiency and accuracy of the heat exchange station and ensures the safe and efficient operation of the heat exchange station. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is a schematic diagram of an unattended heat exchange station monitoring system in a preferred embodiment of the present application;

[0057] Figure 2 It is a flow chart of a control method of an unattended heat exchange station monitoring system in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0058] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0059] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0060] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0061] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0062] like Figure 1 As shown, an unattended heat exchange station monitoring system according to a preferred embodiment of the present application includes:

[0063] A setting module is used to determine multiple demand modules of the heat exchange station and set the focus equipment according to the influence of the heat exchange station equipment on the demand modules;

[0064] A monitoring module is used to pre-set multiple characteristic monitoring indicators, set multiple monitoring points for each device of interest based on the characteristic monitoring indicators, obtain real-time monitoring data of the corresponding device of interest, and generate a monitoring evaluation value of the characteristic monitoring indicator corresponding to the device of interest based on the real-time monitoring data;

[0065] The display module is used to build an association model based on all monitoring points, determine the real-time status of the heat exchange station based on the association model and all monitoring evaluation values, and send the real-time status to the monitoring terminal for display.

[0066] In this embodiment, the demand module of the heat exchange station includes a heat transfer module, a heat supply regulation module, a heat balance module, a waste heat recovery module, etc. The focus device is set according to the functional relationship between the heat exchange station equipment and multiple demand modules and the influence on the demand module. The focus device is the equipment that needs to be monitored, which improves the monitoring efficiency and the accuracy of subsequent monitoring of the status of the heat exchange station.

[0067] In this embodiment, the characteristic monitoring indicators include operating status indicators, heating efficiency indicators, energy consumption indicators, and satisfaction indicators. The monitoring points include but are not limited to points where key monitoring data such as temperature, pressure, and flow of the equipment of interest can be collected. The monitoring data of the monitoring points are mapped to the associated characteristic monitoring indicators, and the real-time monitoring data involved in each characteristic monitoring indicator is analyzed to obtain the monitoring evaluation value of the characteristic monitoring indicator corresponding to the equipment of interest, thereby laying the foundation for the subsequent determination of the real-time status of the heat exchange station. A multi-dimensional analysis is performed based on the monitoring evaluation values ​​of the characteristic monitoring indicators to improve the accuracy of the monitoring results of the heat exchange station.

[0068] In this embodiment, the association model is constructed based on the association relationship of the impact on other monitoring points when a failure occurs at each monitoring point. By constructing the association model and combining the monitoring evaluation values ​​of multiple characteristic monitoring indicators, the real-time status of the heat exchange station is comprehensively determined to improve the accuracy of the heat exchange station status.

[0069] In this embodiment, multiple monitoring data are transmitted to the remote monitoring terminal in real time, and the on-site monitoring data can be collected, analyzed and displayed through the remote monitoring terminal. The monitoring terminal can check the operating status of the on-site equipment at any time, and through remote data analysis and diagnosis, determine the real-time status of the heat exchange station and perform alarm processing and operation and maintenance.

[0070] In some embodiments of the present application, the focus device is set according to the influence of the heat exchange station device on the demand module, including:

[0071] Obtaining specific uses and demand instructions of heat exchange station equipment, determining the functional type of the corresponding heat exchange station equipment according to the specific uses and demand instructions, dividing the heat exchange station equipment of the same functional type into the same demand module, and obtaining multiple demand modules and corresponding heat exchange station equipment;

[0072] Determine multiple operation processes corresponding to the demand module according to the demand instructions of each demand module, and divide the operation processes into main operation processes and secondary operation processes;

[0073] Obtain the first application coefficient and the first important coefficient of the heat exchange station equipment in each demand module for the main operation process and the second application coefficient and the second important coefficient of the secondary operation process;

[0074] Generate a first influence coefficient according to the number of main operation processes whose first application coefficient is greater than the first preset application coefficient, the first application coefficient difference value greater than the first preset application coefficient, the number of main operation processes whose first importance coefficient is greater than the first preset importance coefficient, and the first importance coefficient difference value greater than the first preset importance coefficient;

[0075] Generate a second influence coefficient according to the number of secondary operation processes whose second application coefficient is greater than the second preset application coefficient, the second application coefficient difference value greater than the second preset application coefficient, the number of secondary operation processes whose second importance coefficient is greater than the second preset importance coefficient, and the second importance coefficient difference value greater than the second preset importance coefficient;

[0076] The influence degree of the heat exchange station equipment on the corresponding demand module is generated according to the first influence coefficient and the second influence coefficient.

[0077] In this embodiment, the priority of the work flow is set according to the influence of the work flow on the work result of the demand instruction.

[0078] In this embodiment, the first application coefficient and the second application coefficient respectively refer to the application frequency in the main operation process and the secondary operation process and the application degree of the monitoring data of the heat exchanger station equipment. The application degree of the monitoring data refers to the use of the monitoring data in evaluating the operation effect of the main operation process or the secondary operation process. If the application frequency is high and the application degree is large, the application coefficient is large, otherwise the application coefficient is small. The first influence coefficient and the second influence coefficient respectively refer to the degree of influence of the operation results of the main operation process and the operation results of the secondary operation process. If the influence degree is large, the influence coefficient is large, otherwise the influence coefficient is small.

[0079] In this embodiment, the influence of the heat exchange station equipment on the demand module is determined by dividing the action processes of the demand module into primary and secondary ones, and the application coefficients and importance coefficients of the heat exchange station equipment in the corresponding demand module for the main operation processes and secondary operation processes, thereby determining the focus equipment, laying the foundation for the subsequent calculation of the monitoring evaluation value of each characteristic monitoring indicator, reducing the amount of data monitoring and analysis, and improving monitoring efficiency.

[0080] In some embodiments of the present application, the calculation formula of the influence degree is:

[0081]

[0082] Wherein, Y is the influence degree, c1 is the weight coefficient of the first influence coefficient, m1 is the number of main operation processes whose first application coefficient is greater than the first preset application coefficient, n1 is the total number of main operation processes, △y1i is the ith first application coefficient difference, a1 is the weight coefficient of the first application coefficient, m2 is the number of main operation processes whose first important coefficient is greater than the first preset important coefficient, △z1s is the sth first important coefficient difference, is the first influence coefficient, u1 is the number of secondary operation processes whose second application coefficient is greater than the second preset application coefficient, n2 is the total number of secondary operation processes, △y2r is the rth second application coefficient difference, a2 is the weight coefficient of the second application coefficient, u2 is the number of secondary operation processes whose second important coefficient is greater than the second preset important coefficient, △z2v is the vth second important coefficient difference, b2 is the weight coefficient of the second important coefficient, is the second influence coefficient.

[0083] In this embodiment, when the influence degree is greater, it means that the current heat exchange station equipment has a greater impact on the operation of the corresponding demand module, and the impact on the subsequent monitoring of the heat exchange station status is also greater.

[0084] In some embodiments of the present application, generating a monitoring evaluation value of a characteristic monitoring indicator corresponding to a device of interest according to monitoring-related data includes:

[0085] Preset multiple characteristic monitoring indicators, set monitoring points corresponding to the concerned equipment according to the correlation between the characteristic monitoring indicators and the historical monitoring data of the concerned equipment, configure different sensors for the monitoring points, and set the collection time nodes of the corresponding sensors according to the fluctuation degree of the historical monitoring data corresponding to the multiple sensors at the monitoring points;

[0086] Acquire multiple real-time monitoring data of the monitoring point of the device of interest at the current acquisition time node, compare the real-time monitoring data of the same characteristic monitoring indicator of the current device of interest with the corresponding standard monitoring data, and generate a first evaluation value of the corresponding characteristic monitoring indicator according to the comparison result;

[0087] The real-time monitoring data of the same characteristic monitoring indicator of the focus device at the current acquisition time node is compared with the historical monitoring data corresponding to the previous acquisition time node to obtain multiple fluctuation values, and a compensation coefficient is generated according to the multiple fluctuation values. The first evaluation value is corrected according to the compensation coefficient to obtain the monitoring evaluation value of the corresponding characteristic monitoring indicator of the focus device.

[0088] In this embodiment, the fluctuation value refers to the change in the same real-time monitoring data between the current collection time node and the previous collection time node, and is compared with a standard fluctuation value set in advance. If the fluctuation value is greater than the standard fluctuation value, it means that the corresponding real-time monitoring data has a large fluctuation and low stability, that is, low reliability, then the corresponding compensation coefficient should be smaller, otherwise the compensation coefficient should be larger. The value range of the compensation coefficient is (0.75, 1).

[0089]

[0090] Where J is the monitoring evaluation value, w is the total number of real-time monitoring data corresponding to the characteristic monitoring index of the equipment of interest, hd is the weight coefficient of the d-th real-time monitoring data, gd is the d-th real-time monitoring data, g′d is the d-th standard monitoring data, is the compensation coefficient, p is the compensation conversion coefficient, ld is the fluctuation value of the d-th real-time monitoring data, and l′d is the d-th standard fluctuation value.

[0091] In some embodiments of the present application, a correlation model is constructed based on all monitoring points, including:

[0092] Obtain the historical operation log of each monitoring point, analyze the historical operation log, and filter out the historical fault data and historical normal data of the corresponding monitoring point;

[0093] The historical fault data of each monitoring point is used to determine the triggering of the monitoring point, determine the monitoring point that is triggered in the preset period and obtain the corresponding historical fault data, and use the historical fault data of the current monitoring point as the first training input data set, and the triggered monitoring point and the corresponding historical fault data as the training output label set;

[0094] The historical normal data of each monitoring point is used as a second training input data set, and the monitoring points that have not been triggered within a preset period of time and the corresponding historical normal data are used as a training output unlabeled set;

[0095] Based on the first training input data set, the training output labeled set, the second training input data set and the training output unlabeled set, semi-supervised learning training is performed to generate an association model.

[0096] In this embodiment, the association model is set with labeled data and unlabeled data through a semi-supervised learning method. The combination of labeled data and unlabeled data can overcome the limitation of limited labeled data, provide more data information, and use the structure and distribution of unlabeled data for better modeling and classification, thereby improving the accuracy of the association model, laying the foundation for the subsequent determination of the status of the heat exchange station, and improving the diagnostic accuracy of the status of the heat exchange station.

[0097] In some embodiments of the present application, the real-time status of the heat exchange station is determined according to the correlation model and all monitoring evaluation values, including:

[0098] Obtain the real-time monitoring data of each monitoring point of the equipment of interest, and determine whether the monitoring point has a fault based on the comparison result between the real-time monitoring data and the corresponding standard monitoring data. If so, filter out the faulty monitoring point and obtain the real-time fault data;

[0099] Input the fault monitoring points and real-time fault data into the correlation model, obtain all triggered monitoring points and corresponding real-time fault data, and construct a fault monitoring data set;

[0100] Generate a first state coefficient based on the weight coefficient of the concerned device corresponding to each monitoring point in the fault monitoring data set and the fault degree of the real-time fault data;

[0101] Comprehensively analyze the monitoring evaluation values ​​of the same characteristic monitoring indicators of multiple concerned equipment to obtain the comprehensive monitoring evaluation values ​​of the corresponding characteristic monitoring indicators of the heat exchange station;

[0102] Generate a second state coefficient according to the comprehensive monitoring evaluation values ​​of the multiple characteristic monitoring indicators and the weight coefficients of the corresponding characteristic monitoring indicators;

[0103] Generate a comprehensive state coefficient of the current acquisition time node of the heat exchange station according to the first state coefficient and the second state coefficient;

[0104] Presetting a state coefficient threshold;

[0105] When the comprehensive state coefficient is greater than the state coefficient threshold, the real-time state of the heat exchange station is determined to be a healthy state;

[0106] When the comprehensive state coefficient is less than the state coefficient threshold, the state coefficient difference between the comprehensive state coefficient and the state coefficient threshold is calculated, and the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is determined according to the relationship between the state coefficient difference and the preset state coefficient difference, and the adjustment instruction of the heat exchange station is generated according to the abnormal probability.

[0107] In this embodiment, the impact of each monitoring point failure on other monitoring points is determined based on the association model, the diagnostic accuracy of the heat exchange station status is improved, and the monitoring evaluation values ​​of multiple characteristic monitoring indicators are combined to determine the real-time status of the heat exchange station and the abnormal probability of the heat exchange station, thereby ensuring the safe and efficient operation of the heat exchange station.

[0108] In some embodiments of the present application, a first preset state coefficient difference interval, a second preset state coefficient difference interval, a third preset state coefficient difference interval and a fourth preset state coefficient difference interval are preset;

[0109] When the state coefficient difference is within the first preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is the first preset abnormal probability;

[0110] When the state coefficient difference is in the second preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is the second preset abnormal probability;

[0111] When the state coefficient difference is in the third preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is the third preset abnormal probability;

[0112] When the state coefficient difference is in the fourth preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current collection time node and the next collection time node is the fourth preset abnormal probability.

[0113] In this embodiment, the preset abnormal probability and the preset state coefficient difference interval are set according to historical parameters, and the first preset abnormal probability, the second preset abnormal probability, the third preset abnormal probability, and the fourth preset abnormal probability are 20%, 40%, 60%, and 80%, respectively, and the first preset state coefficient difference interval < the second preset state coefficient difference interval < the third preset state coefficient difference interval < the fourth preset state coefficient difference interval.

[0114] In some embodiments of the present application, generating a regulation instruction for a heat exchange station according to the abnormal probability includes:

[0115] When the abnormal probability is less than or equal to the second preset abnormal probability, a first-level adjustment instruction is generated, wherein the first-level adjustment instruction includes predicting the hidden fault characteristics of the heat exchange station within the time interval between the current acquisition time node and the next acquisition time node;

[0116] When the abnormal probability is between the second preset abnormal probability and the third preset abnormal probability, a secondary adjustment instruction is generated, wherein the secondary adjustment instruction includes determining the hidden fault characteristics of the heat exchange station at the current acquisition time node and configuring a corresponding adjustment strategy for the hidden fault characteristics;

[0117] When the abnormal probability is greater than the third preset abnormal probability, a third adjustment instruction is generated, wherein the third adjustment instruction includes determining the dominant fault feature of the heat exchange station at the current acquisition time node and configuring a corresponding adjustment strategy for the dominant fault feature.

[0118] In this embodiment, the latent fault feature refers to a fault feature that is not obvious or has a small impact at the current acquisition time node, and the explicit fault feature refers to a fault feature that is relatively obvious or has a large impact at the current acquisition time node.

[0119] In this embodiment, the first-level adjustment instruction refers to analyzing the possible causes of abnormalities in subsequent time intervals according to the monitoring evaluation values ​​of the characteristic monitoring indicators corresponding to each monitoring point at the current acquisition time node, and generating corresponding adjustment strategies to ensure efficient and stable operation of the heat exchange station. The second-level adjustment instruction refers to analyzing the possible causes of abnormalities at the current acquisition time node according to the monitoring evaluation values ​​of the characteristic monitoring indicators corresponding to each monitoring point at the current acquisition time node. The third-level adjustment instruction refers to determining the causes of abnormalities at the current acquisition time node according to the monitoring evaluation values ​​of the characteristic monitoring indicators corresponding to each monitoring point at the current acquisition time node, and formulating adjustment strategies.

[0120] In this embodiment, by performing a multi-dimensional analysis on the monitoring evaluation values ​​of all characteristic monitoring indicators and the associated models, the real-time status of the heat exchange station is determined, and the abnormal probability is obtained. According to the abnormal probability, the abnormality of the heat exchange station is predicted or adjusted in time to ensure the safe and efficient operation of the heat exchange station.

[0121] In some embodiments of the present application, Figure 2 As shown, it also includes a control method for an unattended heat exchange station monitoring system:

[0122] Step S201: determining multiple demand modules of a heat exchange station, and setting focus devices according to the influence of the heat exchange station equipment on the demand modules;

[0123] Step S202: pre-set multiple characteristic monitoring indicators, set multiple monitoring points for each device of interest based on the characteristic monitoring indicators, obtain real-time monitoring data of the corresponding device of interest, and generate monitoring evaluation values ​​of the characteristic monitoring indicators corresponding to the device of interest according to the real-time monitoring data;

[0124] Step S203: construct a correlation model based on all monitoring points, determine the real-time status of the heat exchange station based on the correlation model and all monitoring evaluation values, and send the real-time status to the monitoring terminal for display.

[0125] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. An unattended heat exchange station monitoring system, characterized in that: include: A setting module is used to determine multiple demand modules of the heat exchange station and set the focus equipment according to the influence of the heat exchange station equipment on the demand modules; A monitoring module is used to pre-set multiple characteristic monitoring indicators, set multiple monitoring points for each device of interest based on the characteristic monitoring indicators, obtain real-time monitoring data of the corresponding device of interest, and generate a monitoring evaluation value of the characteristic monitoring indicator corresponding to the device of interest based on the real-time monitoring data; The display module is used to build an association model based on all monitoring points, determine the real-time status of the heat exchange station based on the association model and all monitoring evaluation values, and send the real-time status to the monitoring terminal for display.

2. The unattended heat exchange station monitoring system according to claim 1, characterized in that: Set the focus equipment according to the influence of the heat exchange station equipment on the demand module, including: Obtaining specific uses and demand instructions of heat exchange station equipment, determining the functional type of the corresponding heat exchange station equipment according to the specific uses and demand instructions, dividing the heat exchange station equipment of the same functional type into the same demand module, and obtaining multiple demand modules and corresponding heat exchange station equipment; Determine multiple operation processes corresponding to the demand module according to the demand instructions of each demand module, and divide the operation processes into main operation processes and secondary operation processes; Obtain the first application coefficient and the first important coefficient of the heat exchange station equipment in each demand module for the main operation process and the second application coefficient and the second important coefficient of the secondary operation process; Generate a first influence coefficient according to the number of main operation processes whose first application coefficient is greater than the first preset application coefficient, the first application coefficient difference value greater than the first preset application coefficient, the number of main operation processes whose first importance coefficient is greater than the first preset importance coefficient, and the first importance coefficient difference value greater than the first preset importance coefficient; Generate a second influence coefficient according to the number of secondary operation processes whose second application coefficient is greater than the second preset application coefficient, the second application coefficient difference value greater than the second preset application coefficient, the number of secondary operation processes whose second importance coefficient is greater than the second preset importance coefficient, and the second importance coefficient difference value greater than the second preset importance coefficient; The influence degree of the heat exchange station equipment on the corresponding demand module is generated according to the first influence coefficient and the second influence coefficient.

3. The unattended heat exchange station monitoring system according to claim 2, characterized in that: The calculation formula of the influence degree is: Wherein, Y is the influence degree, c1 is the weight coefficient of the first influence coefficient, m1 is the number of main operation processes whose first application coefficient is greater than the first preset application coefficient, n1 is the total number of main operation processes, △y1i is the ith first application coefficient difference, a1 is the weight coefficient of the first application coefficient, m2 is the number of main operation processes whose first important coefficient is greater than the first preset important coefficient, △z1s is the sth first important coefficient difference, is the first influence coefficient, u1 is the number of secondary operation processes whose second application coefficient is greater than the second preset application coefficient, n2 is the total number of secondary operation processes, △y2r is the rth second application coefficient difference, a2 is the weight coefficient of the second application coefficient, u2 is the number of secondary operation processes whose second important coefficient is greater than the second preset important coefficient, △z2v is the vth second important coefficient difference, b2 is the weight coefficient of the second important coefficient, is the second influence coefficient.

4. The unattended heat exchange station monitoring system according to claim 3, characterized in that: Generate monitoring evaluation values ​​of characteristic monitoring indicators corresponding to the equipment of interest based on monitoring-related data, including: Preset multiple characteristic monitoring indicators, set monitoring points corresponding to the concerned equipment according to the degree of correlation between the characteristic monitoring indicators and the historical monitoring data of the concerned equipment, configure different sensors for the monitoring points, and set the collection time nodes of the corresponding sensors according to the fluctuation degree of the historical monitoring data corresponding to the multiple sensors at the monitoring points; Acquire multiple real-time monitoring data of monitoring points of the concerned device at the current acquisition time node, compare the real-time monitoring data of the same characteristic monitoring indicator of the concerned device with the corresponding standard monitoring data, and generate a first evaluation value of the corresponding characteristic monitoring indicator according to the comparison result; The real-time monitoring data of the same characteristic monitoring indicator of the focus device at the current acquisition time node is compared with the historical monitoring data corresponding to the previous acquisition time node to obtain multiple fluctuation values, and a compensation coefficient is generated according to the multiple fluctuation values. The first evaluation value is corrected according to the compensation coefficient to obtain the monitoring evaluation value of the corresponding characteristic monitoring indicator of the focus device.

5. The unattended heat exchange station monitoring system according to claim 4, characterized in that: The calculation formula of the monitoring evaluation value is: Where J is the monitoring evaluation value, w is the total number of real-time monitoring data corresponding to the characteristic monitoring index of the equipment of interest, hd is the weight coefficient of the d-th real-time monitoring data, gd is the d-th real-time monitoring data, g′d is the d-th standard monitoring data, is the compensation coefficient, p is the compensation conversion coefficient, ld is the fluctuation value of the d-th real-time monitoring data, and l′d is the d-th standard fluctuation value.

6. The unattended heat exchange station monitoring system according to claim 5, characterized in that: Build a correlation model based on all monitoring points, including: Obtain the historical operation log of each monitoring point, analyze the historical operation log, and filter out the historical fault data and historical normal data of the corresponding monitoring point; The historical fault data of each monitoring point is used to determine the triggering of the monitoring point, determine the monitoring point that is triggered in the preset period and obtain the corresponding historical fault data, and use the historical fault data of the current monitoring point as the first training input data set, and the triggered monitoring point and the corresponding historical fault data as the training output label set; The historical normal data of each monitoring point is used as the second training input data set, and the monitoring points that have not been triggered within the preset time period and the corresponding historical normal data are used as the training output unlabeled set; Based on the first training input data set, the training output labeled set, the second training input data set and the training output unlabeled set, semi-supervised learning training is performed to generate an association model.

7. The unattended heat exchange station monitoring system according to claim 6, characterized in that: Determine the real-time status of the heat exchange station based on the correlation model and all monitoring and evaluation values, including: Obtain the real-time monitoring data of each monitoring point of the equipment of interest, and determine whether the monitoring point has a fault based on the comparison result between the real-time monitoring data and the corresponding standard monitoring data. If so, filter out the faulty monitoring point and obtain the real-time fault data; Input the fault monitoring points and real-time fault data into the correlation model, obtain all triggered monitoring points and corresponding real-time fault data, and construct a fault monitoring data set; Generate a first state coefficient based on the weight coefficient of the concerned device corresponding to each monitoring point in the fault monitoring data set and the fault degree of the real-time fault data; Comprehensively analyze the monitoring evaluation values ​​of the same characteristic monitoring indicators of multiple concerned equipment to obtain the comprehensive monitoring evaluation values ​​of the corresponding characteristic monitoring indicators of the heat exchange station; Generate a second state coefficient according to the comprehensive monitoring evaluation values ​​of the multiple characteristic monitoring indicators and the weight coefficients of the corresponding characteristic monitoring indicators; Generate a comprehensive state coefficient of the current acquisition time node of the heat exchange station according to the first state coefficient and the second state coefficient; Presetting a state coefficient threshold; When the comprehensive state coefficient is greater than the state coefficient threshold, the real-time state of the heat exchange station is determined to be a healthy state; When the comprehensive state coefficient is less than the state coefficient threshold, the state coefficient difference between the comprehensive state coefficient and the state coefficient threshold is calculated, and the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is determined according to the relationship between the state coefficient difference and the preset state coefficient difference, and the adjustment instruction of the heat exchange station is generated according to the abnormal probability.

8. The unattended heat exchange station monitoring system according to claim 7, characterized in that: Presetting a first preset state coefficient difference interval, a second preset state coefficient difference interval, a third preset state coefficient difference interval and a fourth preset state coefficient difference interval; When the state coefficient difference is in the first preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is the first preset abnormal probability; When the state coefficient difference is in the second preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is the second preset abnormal probability; When the state coefficient difference is in the third preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current acquisition time node and the next acquisition time node is the third preset abnormal probability; When the state coefficient difference is in the fourth preset state coefficient difference interval, the abnormal probability of the heat exchange station in the time interval between the current collection time node and the next collection time node is the fourth preset abnormal probability.

9. The unattended heat exchange station monitoring system according to claim 8, characterized in that: Generate adjustment instructions for the heat exchange station based on the abnormal probability, including: When the abnormal probability is less than or equal to the second preset abnormal probability, a first-level adjustment instruction is generated, wherein the first-level adjustment instruction includes predicting the hidden fault characteristics of the heat exchange station within the time interval between the current acquisition time node and the next acquisition time node; When the abnormal probability is between the second preset abnormal probability and the third preset abnormal probability, a secondary adjustment instruction is generated, wherein the secondary adjustment indicator includes determining the hidden fault characteristics of the heat exchange station at the current acquisition time node and configuring a corresponding adjustment strategy for the hidden fault characteristics; When the abnormal probability is greater than the third preset abnormal probability, a third adjustment instruction is generated, wherein the third adjustment instruction includes determining the dominant fault feature of the heat exchange station at the current acquisition time node and configuring a corresponding adjustment strategy for the dominant fault feature.

10. A control method for an unattended heat exchange station monitoring system, characterized in that: include: Determine multiple demand modules of the heat exchange station, and set the focus equipment according to the influence of the heat exchange station equipment on the demand modules; Preset multiple characteristic monitoring indicators, set multiple monitoring points for each device of interest based on the characteristic monitoring indicators, obtain real-time monitoring data of the corresponding device of interest, and generate monitoring evaluation values ​​of the characteristic monitoring indicators corresponding to the device of interest based on the real-time monitoring data; A correlation model is constructed based on all monitoring points, and the real-time status of the heat exchange station is determined based on the correlation model and all monitoring evaluation values, and the real-time status is sent to the monitoring terminal for display.

Images