Cooler clogging monitoring system with self-cleaning function

Abstract

The invention discloses a cooler clogging monitoring system with a self-cleaning function, and the system comprises an obtaining module which is used for obtaining a historical operation log of a cooler, determining historical characteristic parameters of a plurality of clogging types according to the historical operation log, setting a monitoring scheme corresponding to the historical characteristic parameters according to the change characteristics of the historical characteristic parameters, the monitoring scheme comprises a plurality of monitoring points; the monitoring module is used for acquiring the real-time characteristic parameters of the corresponding monitoring points based on the monitoring scheme, and generating the predicted clogging type and the predicted clogging degree of the cooler according to the change similarity degree of the real-time characteristic parameters and the corresponding historical characteristic parameters; and the control module is used for constructing a control adjustment model library, selecting a feature control adjustment model according to the predicted clogging type and the predicted clogging degree, generating a control instruction of the self-cleaning system according to the feature control adjustment model, and improving the monitoring accuracy of the clogging condition in the cooler and the use efficiency of the cooler.

Description

Technical Field

[0001] The present application relates to the technical field of internal monitoring of coolers, and in particular to a cooler clogging monitoring system with a self-cleaning function. Background Art

[0002] When encountering hot weather and the sedimentation treatment effect is poor during the operation of the clarifier, the dense cold water used for heat exchange contains more impurities, and more impurities will accumulate inside the cooler and adsorb on the inner wall of the heat exchange tube. There is currently no effective monitoring system for whether the inside of the cooler is clogged. If it is not discovered in time, the clogging will accumulate to a certain extent, resulting in poor heat exchange effect of the cooler, and more seriously affecting the performance of the motor and reducing the efficiency of use. Summary of the invention

[0003] In order to solve the above technical problems, the present application provides a cooler blockage monitoring system with a self-cleaning function, which sets a corresponding monitoring scheme according to the change characteristics of the historical characteristic parameters of the blockage type, obtains the real-time characteristic parameters according to the monitoring scheme, and obtains the predicted blockage type and predicted blockage degree of the cooler according to the similarity between the real-time characteristic parameters and the corresponding historical characteristic parameters, selects a characteristic control adjustment model, and generates control instructions for the self-cleaning system according to the characteristic control adjustment model, so as to improve the monitoring accuracy of the blockage situation inside the cooler and the utilization efficiency of the cooler.

[0004] In some embodiments of the present application, a cooler clogging monitoring system with a self-cleaning function is provided, comprising:

[0005] An acquisition module, used for acquiring a historical operation log of the cooler, determining historical characteristic parameters of multiple types of blockage according to the historical operation log, and setting a monitoring scheme corresponding to the historical characteristic parameters according to the change characteristics of the historical characteristic parameters, wherein the monitoring scheme includes multiple monitoring points;

[0006] A monitoring module, which is used to obtain the real-time characteristic parameters of the corresponding monitoring points based on the monitoring scheme, and generate the predicted clogging type and predicted clogging degree of the cooler according to the similarity between the real-time characteristic parameters and the corresponding historical characteristic parameters;

[0007] The control module is used to construct a control and regulation model library, select a characteristic control and regulation model according to the predicted clogging type and predicted clogging degree, and generate control instructions for the self-cleaning system according to the characteristic control and regulation model.

[0008] In some embodiments of the present application, historical characteristic parameters of multiple types of blockage are determined based on historical operation logs, including:

[0009] Obtaining a historical operation log of the cooler, dividing the historical operation log into a historical normal operation log and a historical blockage log, wherein the historical blockage log includes a blockage type and a blockage degree;

[0010] Compare the historical operating parameters in the historical normal operation log with the operating parameters in the historical blockage log to obtain the difference in the historical operating parameters;

[0011] The historical operating parameters whose difference in historical operating parameters is greater than a preset difference threshold are set as pending characteristic parameters of the blockage type corresponding to the historical blockage log;

[0012] The undetermined characteristic parameters of the same blockage type with different blockage degrees are compared, and based on the comparison results, it is determined whether there is a linear relationship between the variables of the same undetermined characteristic parameters with different blockage degrees. If not, the corresponding undetermined characteristic parameters are eliminated; if so, the corresponding undetermined characteristic parameters are set as the historical characteristic parameters of the blockage type.

[0013] In some embodiments of the present application, a monitoring scheme corresponding to the historical characteristic parameters is set according to the change characteristics of the historical characteristic parameters, including:

[0014] Determine the distribution location of the monitoring points of the cooler and the monitoring sensors at the monitoring points according to the data sources of the historical characteristic parameters of each clogging type and the data collection location;

[0015] The historical time period in which the historical characteristic parameters corresponding to the monitoring sensor of the same monitoring point differ from the same historical operating parameters in the historical normal operating log, a parameter change curve is established according to the historical characteristic parameters in the historical time period, the parameter change curve is analyzed, the fluctuation degree of the parameter change curve is determined, and the monitoring time interval of the corresponding monitoring sensor is set according to the fluctuation degree;

[0016] A monitoring plan corresponding to the historical characteristic parameters is generated according to the distribution locations of the monitoring points, the monitoring sensors at the monitoring points and the corresponding monitoring time intervals.

[0017] In some embodiments of the present application, analyzing the parameter change curve to determine the fluctuation degree of the parameter change curve includes:

[0018] Dividing the parameter change curve into a plurality of curve segments according to a preset standard monitoring time interval, calculating a slope threshold of each curve segment, and generating a slope threshold mean of the corresponding parameter change curve according to the plurality of slope thresholds;

[0019] Compare the slope changes of the first curve segment and the last curve segment in the parameter change curve with the slope changes of the remaining curve segments and the adjacent curve segments, and generate the first fluctuation coefficient of the historical characteristic parameter corresponding to the current parameter change curve according to the comparison result and the slope threshold mean;

[0020] Calculate the standard deviation of the corresponding historical characteristic parameter in the historical period according to the parameter change curve, and generate a second fluctuation coefficient according to the standard deviation and average value of the historical characteristic parameter in the historical period;

[0021] The fluctuation degree of the corresponding historical characteristic parameter is generated according to the first fluctuation coefficient and the second fluctuation coefficient.

[0022] In some embodiments of the present application, the monitoring time interval of the corresponding monitoring sensor is set according to the fluctuation degree, including:

[0023] Presetting a first preset fluctuation range, a second preset fluctuation range, a third preset fluctuation range and a fourth preset fluctuation range;

[0024] When the fluctuation degree of the historical characteristic parameter is within the first preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T4=T0*g4;

[0025] When the fluctuation degree of the historical characteristic parameter is within the second preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T3 = T0 * g3;

[0026] When the fluctuation degree of the historical characteristic parameter is within the third preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T2 = T0 * g2;

[0027] When the fluctuation degree of the historical characteristic parameter is within the fourth preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T1 = T0 * g1;

[0028] Among them, T1<T2<T0<T3<T4, 0.75<g1<g2<1<g3<g4<1.25.

[0029] In some embodiments of the present application, the predicted blockage type and predicted blockage degree of the cooler are generated according to the similarity between the real-time characteristic parameter and the corresponding historical characteristic parameter, including:

[0030] Set the target duration in advance and establish a time reference line based on the target duration;

[0031] According to the monitoring time interval corresponding to the real-time characteristic parameter, multiple collection nodes on the time reference line are set, the real-time characteristic parameter is obtained according to the collection node, and mapped to the time reference line to obtain the real-time parameter change curve of the real-time characteristic parameter;

[0032] Each real-time parameter change curve is divided into multiple real-time curve segments according to each acquisition node, and the parameter change curve of the historical characteristic parameter corresponding to the real-time characteristic parameter is divided into multiple historical curve segments according to the time interval between adjacent acquisition nodes;

[0033] Compare the fluctuation degree and parameter interval of the real-time curve segment with the historical curve segment of the corresponding time interval to obtain the fluctuation degree difference and parameter interval difference;

[0034] Generate the degree of similarity between the real-time characteristic parameters and the corresponding historical characteristic parameters according to the fluctuation degree difference and parameter interval difference between the multiple real-time curve segments and the corresponding historical curve segments;

[0035] Pre-set the threshold of change similarity;

[0036] The real-time characteristic parameters whose change similarity is greater than the change similarity threshold are screened out, and a proportion is generated according to the number of congestion types in which the historical characteristic parameters corresponding to the screened real-time characteristic parameters belong and the number of all historical characteristic parameters of the current congestion type;

[0037] The blockage type with a proportion greater than a preset proportion threshold is set as the predicted blockage type of the current cooler;

[0038] The predicted congestion degree of the current predicted congestion type is generated based on the number of real-time feature parameters whose change similarity is greater than the change similarity threshold, the change similarity difference between the change similarity and the change similarity threshold, and the real-time parameter difference between the real-time feature parameters and the corresponding preset standard feature parameters.

[0039] In some embodiments of the present application, the calculation formula for predicting the degree of congestion is:

[0040]

[0041] Among them, Y is the predicted congestion degree, q is the congestion degree conversion coefficient, r is the influence coefficient of the predicted congestion type, n is the number of real-time characteristic parameters whose change similarity is greater than the change similarity threshold, m is the number of all historical characteristic parameters of the current predicted congestion type, △Bi is the i-th change similarity difference, and △Hi is the i-th real-time parameter difference.

[0042] In some embodiments of the present application, a control and regulation model library is constructed, including:

[0043] Obtain the historical cleaning parameters of the self-cleaning system corresponding to the historical blockage log, based on the historical application duration and historical application effect of the historical cleaning parameters;

[0044] Generate an application evaluation value of the corresponding historical cleaning parameter according to the historical application duration and historical application effect of the historical cleaning parameter, select the historical cleaning parameters whose application evaluation value is greater than the preset application evaluation value threshold, and set them as the preferred cleaning parameters corresponding to the blockage type and blockage degree of the historical blockage log;

[0045] According to the preferred cleaning parameters of the same clogging type and the same clogging degree, an initial control and adjustment model corresponding to the clogging type and the clogging degree is established;

[0046] A control and regulation model library is constructed based on the initial control and regulation models of all blockage types and all blockage degrees of each blockage type.

[0047] In some embodiments of the present application, generating control instructions for the self-cleaning system according to the characteristic control adjustment model includes:

[0048] Select the characteristic control and regulation model in the control and regulation model library according to the predicted blockage type and predicted blockage degree;

[0049] Generate control instructions for the self-cleaning system based on the predicted clogging degree and the characteristic control regulation model;

[0050] The real-time cleaning parameters are set according to the control instructions, and the cooler is self-cleaned according to the real-time cleaning parameters. According to the self-cleaning results, it is determined whether the characteristic control adjustment model should be corrected. If corrected, the control adjustment model library is updated.

[0051] Compared with the prior art, the cooler clogging monitoring system with a self-cleaning function in the embodiment of the present application has the following beneficial effects:

[0052] A corresponding monitoring plan is set according to the change characteristics of the historical characteristic parameters of the blockage type, and the real-time characteristic parameters are obtained according to the monitoring plan. According to the similarity between the real-time characteristic parameters and the corresponding historical characteristic parameters, the predicted blockage type and predicted blockage degree of the cooler are obtained, and a characteristic control adjustment model is selected. According to the characteristic control adjustment model, control instructions for the self-cleaning system are generated to improve the monitoring accuracy of the blockage situation inside the cooler and the use efficiency of the cooler. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of a cooler blockage monitoring system with a self-cleaning function in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] like Figure 1 As shown, a cooler clogging monitoring system with a self-cleaning function according to a preferred embodiment of the present application includes:

[0059] An acquisition module, used for acquiring a historical operation log of the cooler, determining historical characteristic parameters of multiple types of blockage according to the historical operation log, and setting a monitoring scheme corresponding to the historical characteristic parameters according to the change characteristics of the historical characteristic parameters, wherein the monitoring scheme includes multiple monitoring points;

[0060] A monitoring module, which is used to obtain the real-time characteristic parameters of the corresponding monitoring points based on the monitoring scheme, and generate the predicted clogging type and predicted clogging degree of the cooler according to the similarity between the real-time characteristic parameters and the corresponding historical characteristic parameters;

[0061] The control module is used to construct a control and regulation model library, select a characteristic control and regulation model according to the predicted clogging type and predicted clogging degree, and generate control instructions for the self-cleaning system according to the characteristic control and regulation model.

[0062] In this embodiment, the types of blockage inside the cooler include scaling, corrosion, pollutants, impurities and precipitation, etc. The historical characteristic parameters of the blockage types refer to the parameters in the historical operating parameters of the cooler that can represent the corresponding blockage types. The change characteristics of the historical characteristic parameters refer to the degree of change of the historical characteristic parameters after the blockage occurs. For example: when the circulating water pump is operating normally, the dense cooling water comes from the dense cooling pump, part of which enters the pump body for sealed cooling, and the other part enters the cooler of the guide bushing on the motor for heat exchange and cooling of the lubricating oil. The inlet pipe and the outlet pipe of the cooler are each provided with a flow meter. By monitoring the flow difference between the outlet pipe and the inlet pipe, the degree of blockage inside the cooler can be monitored.

[0063] In this embodiment, a monitoring scheme is set according to the changing characteristics of historical characteristic parameters, thereby ensuring the monitoring accuracy of the corresponding blockage type and characteristic parameters, improving the monitoring efficiency, timely detecting blockage and setting the cleaning parameters of the self-cleaning system, and improving the use efficiency of the cooler.

[0064] In some embodiments of the present application, historical characteristic parameters of multiple types of blockage are determined based on historical operation logs, including:

[0065] Obtaining a historical operation log of the cooler, dividing the historical operation log into a historical normal operation log and a historical blockage log, wherein the historical blockage log includes a blockage type and a blockage degree;

[0066] Compare the historical operating parameters in the historical normal operation log with the operating parameters in the historical blockage log to obtain the difference in the historical operating parameters;

[0067] The historical operating parameters whose difference in historical operating parameters is greater than a preset difference threshold are set as pending characteristic parameters of the blockage type corresponding to the historical blockage log;

[0068] The undetermined characteristic parameters of the same blockage type with different blockage degrees are compared, and based on the comparison results, it is determined whether there is a linear relationship between the variables of the same undetermined characteristic parameters with different blockage degrees. If not, the corresponding undetermined characteristic parameters are eliminated; if so, the corresponding undetermined characteristic parameters are set as the historical characteristic parameters of the blockage type.

[0069] In some embodiments of the present application, a monitoring scheme corresponding to the historical characteristic parameters is set according to the change characteristics of the historical characteristic parameters, including:

[0070] Determine the distribution location of the monitoring points of the cooler and the monitoring sensors at the monitoring points according to the data sources of the historical characteristic parameters of each clogging type and the data collection location;

[0071] The historical time period in which the historical characteristic parameters corresponding to the monitoring sensor of the same monitoring point differ from the same historical operating parameters in the historical normal operating log, a parameter change curve is established according to the historical characteristic parameters in the historical time period, the parameter change curve is analyzed, the fluctuation degree of the parameter change curve is determined, and the monitoring time interval of the corresponding monitoring sensor is set according to the fluctuation degree;

[0072] A monitoring plan corresponding to the historical characteristic parameters is generated according to the distribution locations of the monitoring points, the monitoring sensors at the monitoring points and the corresponding monitoring time intervals.

[0073] In this embodiment, a reasonable monitoring plan is set according to the changing characteristics of the historical characteristic parameters of each blockage type to facilitate the subsequent collection of real-time characteristic parameters and monitoring accuracy, thereby determining the blockage situation inside the cooler and setting the cleaning parameters of the self-cleaning system to reduce energy consumption, promptly and quickly clear the blockage situation inside the cooler, and improve the use efficiency of the cooler.

[0074] In some embodiments of the present application, analyzing the parameter change curve to determine the fluctuation degree of the parameter change curve includes:

[0075] Dividing the parameter change curve into a plurality of curve segments according to a preset standard monitoring time interval, calculating a slope threshold of each curve segment, and generating a slope threshold mean of the corresponding parameter change curve according to the plurality of slope thresholds;

[0076] Compare the slope changes of the first curve segment and the last curve segment in the parameter change curve with the slope changes of the remaining curve segments and the adjacent curve segments, and generate the first fluctuation coefficient of the historical characteristic parameter corresponding to the current parameter change curve according to the comparison result and the slope threshold mean;

[0077] Calculate the standard deviation of the corresponding historical characteristic parameter in the historical period according to the parameter change curve, and generate a second fluctuation coefficient according to the standard deviation and average value of the historical characteristic parameter in the historical period;

[0078] The fluctuation degree of the corresponding historical characteristic parameter is generated according to the first fluctuation coefficient and the second fluctuation coefficient.

[0079] In this embodiment, the degree of fluctuation = first fluctuation coefficient * 0.6 + second fluctuation coefficient * 0.4. The first fluctuation coefficient is used to measure the change direction and rate of change of the corresponding historical characteristic parameters in the historical time period, and the second fluctuation coefficient is used to measure the change difference of the corresponding historical characteristic parameters in the historical time period. The degree of fluctuation of the historical characteristic parameters after possible blockage can be obtained, which lays the foundation for the subsequent setting of the monitoring time interval of the corresponding characteristic parameters, thereby improving the monitoring accuracy of the characteristic parameters and the use efficiency of the cooler.

[0080] In some embodiments of the present application, the monitoring time interval of the corresponding monitoring sensor is set according to the fluctuation degree, including:

[0081] Presetting a first preset fluctuation range, a second preset fluctuation range, a third preset fluctuation range and a fourth preset fluctuation range;

[0082] When the fluctuation degree of the historical characteristic parameter is within the first preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T4=T0*g4;

[0083] When the fluctuation degree of the historical characteristic parameter is within the second preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T3 = T0 * g3;

[0084] When the fluctuation degree of the historical characteristic parameter is within the third preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T2 = T0 * g2;

[0085] When the fluctuation degree of the historical characteristic parameter is within the fourth preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T1 = T0 * g1;

[0086] Among them, T1<T2<T0<T3<T4, 0.75<g1<g2<1<g3<g4<1.25.

[0087] In this embodiment, when the preset fluctuation degree range is larger, it means that the historical characteristic parameters fluctuate greatly and are prone to abnormalities, that is, the monitoring time interval should be short, and a suitable correction coefficient is selected to correct the preset standard monitoring time interval, so as to collect the corresponding historical characteristic parameters multiple times and accurately monitor the degree of change of the historical characteristic parameters. When the preset fluctuation degree range is smaller, it means that the historical characteristic parameters fluctuate less and are easy to operate stably, that is, the monitoring time interval should be long to reduce energy consumption and parameter processing.

[0088] In this embodiment, a reasonable monitoring time interval is selected according to the degree of fluctuation of the historical characteristic parameters to facilitate the subsequent collection and monitoring accuracy of the real-time characteristic parameters, obtain the degree of change of the real-time characteristic parameter analysis parameters, accurately judge the internal blockage of the cooler according to the degree of change, and perform self-cleaning, thereby restoring the heat exchange effect of the cooler and improving the use efficiency of the cooler.

[0089] In some embodiments of the present application, the predicted blockage type and predicted blockage degree of the cooler are generated according to the similarity between the real-time characteristic parameter and the corresponding historical characteristic parameter, including:

[0090] Set the target duration in advance and establish a time reference line based on the target duration;

[0091] According to the monitoring time interval corresponding to the real-time characteristic parameter, multiple collection nodes on the time reference line are set, the real-time characteristic parameter is obtained according to the collection node, and mapped to the time reference line to obtain the real-time parameter change curve of the real-time characteristic parameter;

[0092] Each real-time parameter change curve is divided into multiple real-time curve segments according to each acquisition node, and the parameter change curve of the historical characteristic parameter corresponding to the real-time characteristic parameter is divided into multiple historical curve segments according to the time interval between adjacent acquisition nodes;

[0093] Compare the fluctuation degree and parameter interval of the real-time curve segment with the historical curve segment of the corresponding time interval to obtain the fluctuation degree difference and parameter interval difference;

[0094] Generate the degree of similarity between the real-time characteristic parameters and the corresponding historical characteristic parameters according to the fluctuation degree difference and parameter interval difference between the multiple real-time curve segments and the corresponding historical curve segments;

[0095] Pre-set the threshold of change similarity;

[0096] The real-time characteristic parameters whose change similarity is greater than the change similarity threshold are screened out, and a proportion is generated according to the number of congestion types in which the historical characteristic parameters corresponding to the screened real-time characteristic parameters belong and the number of all historical characteristic parameters of the current congestion type;

[0097] The blockage type with a proportion greater than a preset proportion threshold is set as the predicted blockage type of the current cooler;

[0098] The predicted congestion degree of the current predicted congestion type is generated based on the number of real-time feature parameters whose change similarity is greater than the change similarity threshold, the change similarity difference between the change similarity and the change similarity threshold, and the real-time parameter difference between the real-time feature parameters and the corresponding preset standard feature parameters.

[0099] In this embodiment, the real-time parameter change curve is constructed based on the moment when the real-time characteristic parameter is greater than the corresponding standard characteristic parameter as the starting point. The parameter interval refers to the interval where the real-time characteristic parameter is located in each real-time curve segment. The real-time curve segment is compared with the parameter interval of the historical curve segment to obtain the parameter interval difference of the corresponding characteristic parameter, and then a comprehensive analysis is performed with the fluctuation degree difference to obtain the degree of change similarity.

[0100] In this embodiment, the predicted blockage type is obtained based on the screened real-time characteristic parameters and the proportion of multiple blockage types, and the predicted blockage degree is generated based on the difference in change similarity and the difference in real-time parameters. The characteristic control adjustment model is selected based on the predicted blockage type and the predicted blockage degree, and the cleaning parameters of the self-cleaning system are obtained to improve the monitoring efficiency and utilization efficiency of the cooler.

[0101] In some embodiments of the present application, the calculation formula for predicting the degree of congestion is:

[0102]

[0103] Among them, Y is the predicted congestion degree, q is the congestion degree conversion coefficient, r is the influence coefficient of the predicted congestion type, n is the number of real-time characteristic parameters whose change similarity is greater than the change similarity threshold, m is the number of all historical characteristic parameters of the current predicted congestion type, △Bi is the i-th change similarity difference, and △Hi is the i-th real-time parameter difference.

[0104] In some embodiments of the present application, a control and regulation model library is constructed, including:

[0105] Obtain the historical cleaning parameters of the self-cleaning system corresponding to the historical blockage log, based on the historical application duration and historical application effect of the historical cleaning parameters;

[0106] Generate an application evaluation value of the corresponding historical cleaning parameter according to the historical application duration and historical application effect of the historical cleaning parameter, select the historical cleaning parameters whose application evaluation value is greater than the preset application evaluation value threshold, and set them as the preferred cleaning parameters corresponding to the blockage type and blockage degree of the historical blockage log;

[0107] According to the preferred cleaning parameters of the same clogging type and the same clogging degree, an initial control and adjustment model corresponding to the clogging type and the clogging degree is established;

[0108] A control and regulation model library is constructed based on the initial control and regulation models of all blockage types and all blockage degrees of each blockage type.

[0109] In this embodiment, corresponding initial control and adjustment models are established according to different blockage types and multiple blockage degrees to achieve preferential control of the cleaning parameters of the self-cleaning system, thereby improving the cleaning efficiency of the cooler in different blockage types and different blockage degrees, thereby improving the utilization efficiency of the cooler.

[0110] In some embodiments of the present application, generating control instructions for the self-cleaning system according to the characteristic control adjustment model includes:

[0111] Select the characteristic control and regulation model in the control and regulation model library according to the predicted blockage type and predicted blockage degree;

[0112] Generate control instructions for the self-cleaning system based on the predicted clogging degree and the characteristic control regulation model;

[0113] The real-time cleaning parameters are set according to the control instructions, and the cooler is self-cleaned according to the real-time cleaning parameters. According to the self-cleaning results, it is determined whether the characteristic control adjustment model should be corrected. If corrected, the control adjustment model library is updated.

[0114] In this embodiment, the self-cleaning result, that is, the application evaluation value of the real-time cleaning parameter, if the application evaluation value is greater than the preset application evaluation value threshold, the characteristic control adjustment model is not corrected; if it is not greater than the preset application evaluation value threshold, the characteristic control adjustment model is corrected, and the initial control adjustment model in the control adjustment model library is continuously updated to improve the self-cleaning effect of different blockage types and blockage degrees of the cooler, thereby improving the use efficiency of the cooler.

[0115] 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. A cooler clogging monitoring system with self-cleaning function, characterized in that: include: An acquisition module, used for acquiring a historical operation log of the cooler, determining historical characteristic parameters of multiple types of blockage according to the historical operation log, and setting a monitoring scheme corresponding to the historical characteristic parameters according to the change characteristics of the historical characteristic parameters, wherein the monitoring scheme includes multiple monitoring points; A monitoring module, which is used to obtain the real-time characteristic parameters of the corresponding monitoring points based on the monitoring scheme, and generate the predicted clogging type and predicted clogging degree of the cooler according to the similarity between the real-time characteristic parameters and the corresponding historical characteristic parameters; The control module is used to construct a control and regulation model library, select a characteristic control and regulation model according to the predicted clogging type and predicted clogging degree, and generate control instructions for the self-cleaning system according to the characteristic control and regulation model.

2. The cooler clogging monitoring system with self-cleaning function according to claim 1, characterized in that: The historical characteristic parameters of multiple types of blockage are determined based on historical operation logs, including: Obtaining a historical operation log of the cooler, dividing the historical operation log into a historical normal operation log and a historical blockage log, wherein the historical blockage log includes a blockage type and a blockage degree; Compare the historical operating parameters in the historical normal operation log with the operating parameters in the historical blockage log to obtain the difference in the historical operating parameters; The historical operating parameters whose difference in historical operating parameters is greater than a preset difference threshold are set as pending characteristic parameters of the blockage type corresponding to the historical blockage log; The undetermined characteristic parameters of the same blockage type with different blockage degrees are compared, and based on the comparison results, it is determined whether there is a linear relationship between the variables of the same undetermined characteristic parameters with different blockage degrees. If not, the corresponding undetermined characteristic parameters are eliminated; if so, the corresponding undetermined characteristic parameters are set as the historical characteristic parameters of the blockage type.

3. The cooler clogging monitoring system with self-cleaning function as claimed in claim 2, characterized in that: According to the change characteristics of the historical characteristic parameters, the monitoring plan corresponding to the historical characteristic parameters is set, including: Determine the distribution location of the monitoring points of the cooler and the monitoring sensors at the monitoring points according to the data sources of the historical characteristic parameters of each clogging type and the data collection location; The historical time period in which the historical characteristic parameters corresponding to the monitoring sensor of the same monitoring point differ from the same historical operating parameters in the historical normal operating log, a parameter change curve is established according to the historical characteristic parameters in the historical time period, the parameter change curve is analyzed, the fluctuation degree of the parameter change curve is determined, and the monitoring time interval of the corresponding monitoring sensor is set according to the fluctuation degree; A monitoring plan corresponding to the historical characteristic parameters is generated according to the distribution locations of the monitoring points, the monitoring sensors at the monitoring points and the corresponding monitoring time intervals.

4. The cooler clogging monitoring system with self-cleaning function as claimed in claim 3, characterized in that: Analyze the parameter change curve to determine the fluctuation degree of the parameter change curve, including: Dividing the parameter change curve into a plurality of curve segments according to a preset standard monitoring time interval, calculating a slope threshold of each curve segment, and generating a slope threshold mean of the corresponding parameter change curve according to the plurality of slope thresholds; Compare the slope changes of the first curve segment and the last curve segment in the parameter change curve with the slope changes of the remaining curve segments and the adjacent curve segments, and generate the first fluctuation coefficient of the historical characteristic parameter corresponding to the current parameter change curve according to the comparison result and the slope threshold mean; Calculate the standard deviation of the corresponding historical characteristic parameter in the historical period according to the parameter change curve, and generate a second fluctuation coefficient according to the standard deviation and average value of the historical characteristic parameter in the historical period; The fluctuation degree of the corresponding historical characteristic parameter is generated according to the first fluctuation coefficient and the second fluctuation coefficient.

5. The cooler clogging monitoring system with self-cleaning function as claimed in claim 4, characterized in that: Set the monitoring time interval of the corresponding monitoring sensor according to the degree of fluctuation, including: Presetting a first preset fluctuation range, a second preset fluctuation range, a third preset fluctuation range and a fourth preset fluctuation range; When the fluctuation degree of the historical characteristic parameter is within the first preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T4=T0*g4; When the fluctuation degree of the historical characteristic parameter is within the second preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T3 = T0 * g3; When the fluctuation degree of the historical characteristic parameter is within the third preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T2 = T0 * g2; When the fluctuation degree of the historical characteristic parameter is within the fourth preset fluctuation degree range, the monitoring time interval of the corresponding monitoring sensor is set to the fourth preset monitoring time interval T4, and T1 = T0 * g1; Among them, T1<T2<T0<T3<T4, 0.75<g1<g2<1<g3<g4<1.

25.

6. The cooler clogging monitoring system with self-cleaning function as claimed in claim 5, characterized in that: According to the similarity between the real-time characteristic parameters and the corresponding historical characteristic parameters, the predicted blockage type and predicted blockage degree of the cooler are generated, including: Set the target duration in advance and establish a time reference line based on the target duration; According to the monitoring time interval corresponding to the real-time characteristic parameter, multiple collection nodes on the time reference line are set, the real-time characteristic parameter is obtained according to the collection node, and mapped to the time reference line to obtain the real-time parameter change curve of the real-time characteristic parameter; Each real-time parameter change curve is divided into multiple real-time curve segments according to each acquisition node, and the parameter change curve of the historical characteristic parameter corresponding to the real-time characteristic parameter is divided into multiple historical curve segments according to the time interval between adjacent acquisition nodes; Compare the fluctuation degree and parameter interval of the real-time curve segment with the historical curve segment of the corresponding time interval to obtain the fluctuation degree difference and parameter interval difference; Generate the degree of similarity between the real-time characteristic parameters and the corresponding historical characteristic parameters according to the fluctuation degree difference and parameter interval difference between the multiple real-time curve segments and the corresponding historical curve segments; Pre-set the threshold of change similarity; The real-time characteristic parameters whose change similarity is greater than the change similarity threshold are screened out, and a proportion is generated according to the number of congestion types in which the historical characteristic parameters corresponding to the screened real-time characteristic parameters belong and the number of all historical characteristic parameters of the current congestion type; The blockage type with a proportion greater than a preset proportion threshold is set as the predicted blockage type of the current cooler; The predicted congestion degree of the current predicted congestion type is generated based on the number of real-time feature parameters whose change similarity is greater than the change similarity threshold, the change similarity difference between the change similarity and the change similarity threshold, and the real-time parameter difference between the real-time feature parameters and the corresponding preset standard feature parameters.

7. The cooler clogging monitoring system with self-cleaning function as claimed in claim 6, characterized in that: The calculation formula for predicting the degree of clogging is: Among them, Y is the predicted congestion degree, q is the congestion degree conversion coefficient, r is the influence coefficient of the predicted congestion type, n is the number of real-time characteristic parameters whose change similarity is greater than the change similarity threshold, m is the number of all historical characteristic parameters of the current predicted congestion type, △Bi is the i-th change similarity difference, and △Hi is the i-th real-time parameter difference.

8. The cooler clogging monitoring system with self-cleaning function as claimed in claim 7, characterized in that: Build a control and regulation model library, including: Obtain the historical cleaning parameters of the self-cleaning system corresponding to the historical blockage log, based on the historical application duration and historical application effect of the historical cleaning parameters; Generate an application evaluation value of the corresponding historical cleaning parameter according to the historical application duration and historical application effect of the historical cleaning parameter, select the historical cleaning parameters whose application evaluation value is greater than the preset application evaluation value threshold, and set them as the preferred cleaning parameters corresponding to the blockage type and blockage degree of the historical blockage log; According to the preferred cleaning parameters of the same clogging type and the same clogging degree, an initial control and adjustment model corresponding to the clogging type and the clogging degree is established; A control and regulation model library is constructed based on the initial control and regulation models of all blockage types and all blockage degrees of each blockage type.

9. The cooler clogging monitoring system with self-cleaning function as claimed in claim 8, characterized in that: Generate control instructions for the self-cleaning system based on the characteristic control adjustment model, including: Select the characteristic control and regulation model in the control and regulation model library according to the predicted blockage type and predicted blockage degree; Generate control instructions for the self-cleaning system based on the predicted clogging degree and the characteristic control regulation model; The real-time cleaning parameters are set according to the control instructions, and the cooler is self-cleaned according to the real-time cleaning parameters. According to the self-cleaning results, it is determined whether the characteristic control adjustment model should be corrected. If corrected, the control adjustment model library is updated.

Images