Condenser cleaning strategy management method and device based on operating mode, equipment and storage medium

Abstract

The application discloses a condenser cleaning strategy management method and device based on an operation mode, an equipment and a storage medium, relates to the technical field of condenser cleaning, and the condenser cleaning strategy management method based on the operation mode comprises the following steps: through change trend prediction of a cleaning coefficient and a vacuum degree based on a dirt diagnosis result and a current operation mode, future working condition prediction of the condenser is realized, unnecessary shutdown caused by cleaning according to a fixed period and emergency shutdown caused by sudden deterioration of the vacuum degree and the like are avoided; and through generation of a cleaning strategy of the condenser according to the dirt diagnosis result and a cleaning prediction result, the cleaning of the condenser can dynamically adjust a cleaning time, a cleaning mode and the like according to dirt quantity and prediction, and adaptability and dynamic change capability of the condenser cleaning are improved.

Description

Technical Field

[0001] This application relates to the field of condenser cleaning technology, and in particular to a condenser cleaning strategy management method, apparatus, equipment and storage medium based on operating modes. Background Technology

[0002] Condensers are devices used in thermal power plants, nuclear power plants, and other similar settings to improve the efficiency of the heat cycle. During condenser operation, the temperature difference between the cooling water inside and outside the heat exchange tubes and the high-temperature exhaust steam can easily lead to fouling on the inner and outer walls of the heat exchange tubes, thus affecting the heat exchange efficiency of the condenser.

[0003] Currently, existing condenser cleaning methods mainly include online cleaning and offline cleaning. However, both online and offline cleaning are performed periodically according to a preset fixed cycle, which can easily lead to over-cleaning or under-cleaning. Summary of the Invention

[0004] The main purpose of this application is to provide a condenser cleaning strategy management method, device, equipment and storage medium based on operating modes, which aims to solve the technical problem that fixed condenser cleaning cycles can easily lead to over-cleaning or under-cleaning.

[0005] To achieve the above objectives, this application proposes a condenser cleaning strategy management method based on operating modes, the method comprising: Determine the current operating mode of the condenser and obtain the mode cleaning and identification model corresponding to the current operating mode; Acquire multi-dimensional data of condenser operation, and perform fouling diagnosis on the multi-dimensional data through the modal cleaning recognition model to obtain fouling diagnosis results; Based on the fouling diagnosis results and the current operating mode, the changing trends of the condenser's cleanliness coefficient and vacuum level are predicted to obtain cleaning prediction results; A cleaning strategy for the condenser is generated based on the fouling diagnosis results and the cleaning prediction results.

[0006] In one embodiment, the step of predicting the changing trends of the condenser's cleanliness coefficient and vacuum degree based on the fouling diagnosis results and the current operating mode to obtain cleaning prediction results includes: An initial state vector is constructed based on the current cleanliness coefficient and current vacuum level corresponding to the dirt diagnosis results; Based on the model parameters corresponding to the current operating mode and the initial state vector, a prior estimate of the initial state vector at the next moment is determined; The prior estimate is used as a new initial state vector, and the process of determining the prior estimate of the initial state vector at the next moment based on the model parameters corresponding to the current running mode and the initial state vector is repeated until the number of prior estimates obtained is greater than the maximum number of sequences. A state vector change trend sequence is constructed based on the prior estimates at each time point, and the state vector change trend sequence is used as the cleaning prediction result.

[0007] In one embodiment, the model parameters include the dirt accumulation rate and the vacuum decay sensitivity coefficient; The step of determining the prior estimate of the initial state vector at the next moment based on the model parameters corresponding to the current operating mode and the initial state vector includes: Obtain the fouling accumulation rate coefficient and vacuum attenuation sensitivity coefficient corresponding to the current operating mode; The cleaning factor for the next moment is predicted based on the dirt accumulation rate coefficient and the sampling time interval; Predict the vacuum level at the next moment based on the vacuum level decay sensitivity coefficient; The prior estimate of the initial state vector at the next time step is obtained based on the cleanliness coefficient and the vacuum degree at the next time step.

[0008] In one embodiment, the step of generating a cleaning strategy for the condenser based on the fouling diagnosis results and the cleaning prediction results includes: The cleaning priority of the condenser is determined based on the threshold range of the fouling diagnosis results. The cleaning method and target cleaning threshold of the condenser are determined based on the cleaning priority. The time point corresponding to the prior estimate of the target cleaning threshold in the state vector change trend sequence is taken as the cleaning time point. A cleaning strategy for the condenser is generated based on the cleaning method and the cleaning time point.

[0009] In one embodiment, the step of determining the cleaning method and target cleaning threshold of the condenser based on the cleaning priority includes: The cleaning threshold adjustment parameters are determined based on the cleaning priority. The cleaning method for the condenser is determined based on the cleaning priority; and... The current cleaning coefficient corresponding to the dirt diagnosis result is dynamically adjusted according to the cleaning threshold adjustment parameter to obtain the target cleaning threshold.

[0010] In one embodiment, the step of performing dirt diagnosis on the multi-dimensional data using the modal cleaning recognition model to obtain dirt diagnosis results includes: The heat transfer coefficient and vacuum level of the cleaning state corresponding to the modal cleaning identification model are determined. Based on the multi-dimensional data, the current actual heat transfer coefficient and the current actual vacuum level of the condenser are determined. The current cleanliness coefficient of the condenser is determined based on the heat transfer coefficient under clean conditions and the current actual heat transfer coefficient. The current vacuum deviation of the condenser is determined based on the vacuum level under clean conditions and the current actual vacuum level. The dirt diagnosis result is determined based on the current cleanliness coefficient and the current vacuum deviation.

[0011] In one embodiment, before the step of obtaining the mode cleaning and recognition model corresponding to the current operating mode, the method further includes: Obtain multi-dimensional historical datasets; Clustering is performed on the multi-dimensional historical dataset to obtain modal data clusters; The heat transfer coefficient and vacuum degree in the clean state of each modal data cluster were determined. Based on the heat transfer coefficient and vacuum degree of the clean state, a modal cleaning identification model is constructed for each modal data cluster.

[0012] Furthermore, to achieve the above objectives, this application also proposes a condenser cleaning strategy management device based on operating modes, the condenser cleaning strategy management device based on operating modes comprising: The mode management module is used to determine the current operating mode of the condenser and obtain the mode cleaning and identification model corresponding to the current operating mode; The fouling diagnosis module is used to acquire multi-dimensional data of condenser operation and perform fouling diagnosis on the multi-dimensional data through the modal cleaning recognition model to obtain fouling diagnosis results. The cleaning prediction module is used to predict the changing trends of the cleanliness coefficient and vacuum degree of the condenser based on the fouling diagnosis results and the current operating mode, and to obtain the cleaning prediction results. The strategy management module is used to generate a cleaning strategy for the condenser based on the fouling diagnosis results and the cleaning prediction results.

[0013] Furthermore, to achieve the above objectives, this application also proposes a condenser cleaning strategy management device based on operating modes. The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the condenser cleaning strategy management method based on operating modes as described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the condenser cleaning strategy management method based on operating modes as described above.

[0015] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the condenser cleaning strategy management method based on operating modes as described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: This application determines the current operating mode of the condenser and obtains the corresponding modal cleaning identification model. It acquires multi-dimensional data on condenser operation and uses the modal cleaning identification model to diagnose fouling, obtaining fouling diagnosis results. Based on the fouling diagnosis results and the current operating mode, it predicts the changing trends of the condenser's cleanliness coefficient and vacuum level, obtaining cleaning prediction results. Finally, it generates a condenser cleaning strategy based on the fouling diagnosis results and cleaning prediction results. Because the current operating mode of the condenser is determined, interference from operating condition fluctuations can be eliminated, significantly improving the accuracy of fouling diagnosis and enhancing its dynamic tracking capability. Using the modal cleaning identification model to diagnose fouling from multi-dimensional condenser operation data avoids the limitations of single-parameter judgments and can promptly detect potential fouling problems in the early stages of slight performance degradation in the condenser, enabling predictive maintenance. By predicting the changing trends of the cleanliness coefficient and vacuum level based on the fouling diagnosis results and the current operating mode, the future operating conditions of the condenser can be predicted, avoiding unnecessary shutdowns caused by fixed-cycle cleaning and emergency shutdowns caused by sudden deterioration of vacuum level. By generating a condenser cleaning strategy based on the fouling diagnosis results and cleaning prediction results, the cleaning time and cleaning method of the condenser can be dynamically adjusted according to the amount of fouling and the predicted amount, thereby improving the adaptability and dynamic change capability of condenser cleaning. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the condenser cleaning strategy management method based on operating modes in this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the condenser cleaning strategy management method based on operating modes provided in this application; Figure 3 This is a flowchart illustrating Embodiment 3 of the condenser cleaning strategy management method based on operating modes provided in this application; Figure 4 This is a schematic diagram of the module structure of the condenser cleaning strategy management device based on operating mode according to an embodiment of this application; Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the condenser cleaning strategy management method based on operating mode in the embodiments of this application.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of this application embodiment is as follows: determine the current operating mode of the condenser and obtain the mode cleaning recognition model corresponding to the current operating mode; obtain multi-dimensional data of the condenser operation and perform fouling diagnosis on the multi-dimensional data through the mode cleaning recognition model to obtain fouling diagnosis results; predict the changing trends of the condenser's cleanliness coefficient and vacuum degree based on the fouling diagnosis results and the current operating mode to obtain cleaning prediction results; and generate a condenser cleaning strategy based on the fouling diagnosis results and the cleaning prediction results.

[0024] This application provides a solution that, by determining the current operating mode of the condenser, eliminates interference caused by fluctuations in operating conditions, significantly improving the accuracy of fouling diagnosis and enhancing its dynamic tracking capability. By using a modal cleaning identification model to diagnose fouling based on multi-dimensional data of condenser operation, it avoids the limitations of single-parameter judgments and can promptly detect potential fouling problems in the early stages of slight performance degradation, enabling predictive maintenance. By predicting the changing trends of the cleanliness coefficient and vacuum level based on fouling diagnosis results and the current operating mode, it achieves prediction of the condenser's future operating conditions, avoiding unnecessary shutdowns caused by fixed-cycle cleaning and emergency shutdowns due to sudden deterioration of vacuum. Furthermore, by generating a condenser cleaning strategy based on fouling diagnosis and cleaning prediction results, the cleaning time and method can be dynamically adjusted according to the amount of fouling and the predicted amount, improving the adaptability and dynamic change capability of condenser cleaning.

[0025] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a computer, server, industrial control terminal, etc., or an electronic device or virtual device capable of realizing the above functions. The following description uses a condenser cleaning strategy management device based on operating modes (hereinafter referred to as the management device) as an example to illustrate this embodiment and the following embodiments.

[0026] Based on this, embodiments of this application provide a condenser cleaning strategy management method based on operating modes, referring to... Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the condenser cleaning strategy management method based on operating modes in this application.

[0027] In this embodiment, the condenser cleaning strategy management method based on operating modes includes steps S10~S40: Step S10: Determine the current operating mode of the condenser and obtain the mode cleaning and identification model corresponding to the current operating mode.

[0028] In this embodiment, several operating modes can be set for the condenser. These operating modes can characterize the operating conditions of the condenser and its associated unit within a certain time period. Under different operating modes, the thermodynamic characteristics, fouling formation patterns, and performance degradation rates of the condenser vary. By determining the current operating mode of the condenser, a modal cleaning identification model, diagnostic parameters, and prediction algorithms adapted to the current operating conditions of the condenser can be matched and applied.

[0029] For example, the operating modes in the embodiments of this application can be divided according to the unit's load level and environmental conditions, and the embodiments of this application do not limit this. For example, when the unit's load is greater than the first rated load (e.g., 85%), the current operating mode of the condenser can be determined as the high-load steady-state operating mode; when the unit's load is greater than the second rated load (e.g., 50%) but not greater than the first rated load, the current operating mode of the condenser can be determined as the medium-load operating mode; when the unit's load is not greater than the second rated load, the current operating mode of the condenser can be determined as the low-load operating mode.

[0030] Understandably, the baseline operating parameters of the condenser (such as the clean-state heat transfer coefficient, clean-state vacuum, fouling rate coefficient, cleanliness coefficient, and vacuum decay sensitivity coefficient) differ under different operating modes. For example, under high-load steady-state operating mode, the clean-state heat transfer coefficient and fouling rate coefficient of the condenser may be relatively high.

[0031] It should be understood that the heat transfer coefficient can be used as an indicator to measure the heat transfer efficiency of a condenser, characterizing the condenser's ability to transfer heat per unit area and per unit temperature difference. In practical applications, the heat transfer coefficient can be calculated based on the condenser's heat balance, and this application embodiment does not impose specific restrictions on its acquisition method. The aforementioned clean-state heat transfer coefficient is the heat transfer coefficient of the condenser in a clean state under the corresponding operating mode.

[0032] It is understood that vacuum degree can be used to characterize the degree to which the internal pressure of a condenser is lower than atmospheric pressure. The lower the cleanliness of the condenser, the more likely it is to lead to deterioration in heat transfer, thereby causing a decrease in vacuum degree. This application does not limit the specific method for obtaining vacuum degree in its embodiments; it can be selected according to the actual application. The aforementioned vacuum degree in the clean state is the vacuum degree of the condenser in a clean state under the corresponding operating mode.

[0033] It should be understood that the aforementioned fouling accumulation rate coefficient can be a parameter used to characterize the amount of reduction in the cleanliness coefficient per unit time, reflecting the rate at which fouling deposits in the condenser tubes under the current operating mode. The larger the fouling accumulation rate coefficient, the faster the fouling accumulates.

[0034] It is understood that the cleanliness factor in this application embodiment is a measure of the degree to which the current heat transfer performance of the condenser is maintained. Specifically, the current cleanliness factor can be represented by the ratio of the current actual heat transfer factor to the heat transfer factor in the clean state, and its expression is as follows: ; in, Indicates the cleanliness factor. This represents the current actual heat transfer coefficient. This represents the heat transfer coefficient in a clean state.

[0035] It should be noted that the aforementioned modal cleaning identification model can be an intelligent model composed of multiple sub-modules, used to realize fouling diagnosis, trend prediction, and strategy recommendation functions. Specifically, the modal cleaning identification model in this application embodiment may include a fouling diagnosis module, a trend prediction module, and a strategy recommendation module. Through these modules, fouling diagnosis results can be obtained by performing fouling diagnosis on multi-dimensional data; the changing trends of the condenser's cleanliness coefficient and vacuum degree can be predicted based on the fouling diagnosis results and the current operating mode, resulting in cleaning prediction results; and cleaning strategies for the condenser can be generated based on the fouling diagnosis results and cleaning prediction results, etc., which are not limited in this application embodiment.

[0036] In some embodiments of this application, in order to generate a modal cleaning identification model, before the step of obtaining the modal cleaning identification model corresponding to the currently running modality, the method further includes: obtaining a multi-dimensional historical dataset; performing clustering based on the multi-dimensional historical dataset to obtain modal data clusters; determining the heat transfer coefficient and vacuum degree of each modal data cluster in the cleaning state; and constructing a modal cleaning identification model corresponding to each modal data cluster based on the heat transfer coefficient and vacuum degree of the cleaning state.

[0037] It should be noted that multi-dimensional historical data can be multi-dimensional data collected based on historical operating data of condensers, units, etc. This multi-dimensional historical data can cover all operating conditions of the condenser and multiple operating cycles. The aforementioned multi-dimensional historical dataset is a collection of data composed of multi-dimensional historical data.

[0038] In some embodiments of this application, when generating a modal cleaning and identification model, clustering can be performed based on a multi-dimensional historical dataset to obtain modal data clusters.

[0039] It is understandable that clustering is an unsupervised learning method that can divide a dataset into multiple modal data clusters based on data characteristics. Data in the same modal data cluster has high similarity, while data in different modal data clusters has low similarity.

[0040] In the embodiments of this application, clustering can be performed based on multi-dimensional historical data of condenser operation under different operating conditions and different cycles, and the data can be automatically classified into several condenser operating modes, such as the low-load operating mode, medium-load operating mode and high-load steady-state operating mode mentioned above.

[0041] In some embodiments of this application, the clustering algorithm used may be K-means clustering. Specifically, this application embodiment may first construct modal feature vectors based on multi-dimensional historical data. These modal feature vectors may include features such as load rate, ambient temperature, circulating water flow rate, circulating water inlet temperature, and circulating water outlet temperature; this application embodiment does not impose any limitations on this. A dissimilarity matrix is ​​constructed based on the modal feature vectors, and data dimensionality reduction is performed based on the average distance between the feature vectors, resulting in a dimensionality-reduced mapping from a multi-dimensional feature space to a one-dimensional distance space. K-means clustering is then performed on the dimensionality-reduced dataset to obtain the clusters corresponding to each modality.

[0042] It is understood that in practical applications, other clustering methods can also be used to generate modal data clusters, and the embodiments of this application do not limit this.

[0043] It should be noted that when obtaining modal data clusters, for each modal data cluster, the characteristic distribution of the modal data cluster can be statistically analyzed, and benchmark parameters (i.e., clean state heat transfer coefficient, clean state heat transfer coefficient vacuum degree, dirt accumulation rate coefficient, vacuum degree decay sensitivity coefficient, etc.) can be calculated based on these characteristic distributions. Then, a modal cleaning identification model can be obtained based on these benchmark parameters.

[0044] In a specific implementation, the management device of this application embodiment can determine the current operating mode of the condenser and determine the modal cleaning identification model required for condenser cleaning strategy management based on the current operating mode of the condenser, thereby avoiding interference caused by operating condition fluctuations, significantly improving the accuracy of fouling diagnosis, and enhancing the dynamic tracking capability of fouling diagnosis.

[0045] Step S20: Obtain multi-dimensional data of condenser operation, and perform fouling diagnosis on the multi-dimensional data through the modal cleaning recognition model to obtain fouling diagnosis results.

[0046] It is understood that the aforementioned multi-dimensional data refers to the various types and dimensions of data involved in the current operation of the condenser, such as circulating water inlet temperature, circulating water outlet temperature, exhaust steam temperature, ambient temperature, current actual vacuum degree, circulating water pressure, circulating water flow rate, unit load data, etc. This application embodiment does not limit these.

[0047] It should be understood that when determining the current operating mode of the condenser, it can be based on the above-mentioned multi-dimensional data, or it can be obtained directly from the current operating condition of the condenser. This application embodiment does not impose any restrictions on this.

[0048] It should be noted that the modal cleaning identification model in this application embodiment may include a fouling diagnosis module. Based on multi-dimensional data, parameters such as the current actual heat transfer coefficient, current actual vacuum degree, and thermal resistance of the condenser can be determined. Based on these parameters, the fouling diagnosis module can perform fouling diagnosis, thereby determining the fouling diagnosis result of the condenser. The fouling diagnosis result may include the performance status of the condenser, which can be represented by a cleanliness coefficient or by the range in which the cleanliness coefficient falls, such as clean state, light fouling, moderate fouling, heavy fouling, etc. It may also include diagnostic confidence level, operating mode, etc., which are not limited in this application embodiment.

[0049] In its specific implementation, the management device in this embodiment can acquire multi-dimensional data on condenser operation. The fouling diagnosis module of the modal cleaning identification model then performs fouling diagnosis on this multi-dimensional data to obtain the condenser's fouling diagnosis results. Using the modal cleaning identification model to diagnose fouling based on multi-dimensional data avoids the limitations of judging from a single parameter, enabling timely detection of potential fouling problems in the early stages of slight performance degradation in the condenser, thus achieving predictive maintenance.

[0050] Step S30: Based on the fouling diagnosis results and the current operating mode, predict the changing trends of the condenser's cleanliness coefficient and vacuum level to obtain cleaning prediction results; Step S40: Generate a cleaning strategy for the condenser based on the fouling diagnosis results and the cleaning prediction results.

[0051] It should be noted that, based on the fouling diagnosis module and the current operating mode of the condenser, the changing trends of the current actual cleanliness coefficient and the current actual vacuum degree of the condenser can be predicted. This allows for the determination of the future trends in both cleanliness coefficient and vacuum degree, i.e., the cleaning prediction result. Based on this prediction result, the appropriate cleaning time for condenser cleaning can be determined. Furthermore, based on the fouling diagnosis result, the required cleaning method can be determined, such as online cleaning (ball cleaning, low-pressure water cleaning, etc.), chemical cleaning, or shutdown cleaning.

[0052] In its specific implementation, the management device in this application embodiment can predict the changing trends of the condenser's cleanliness coefficient and vacuum degree based on the fouling diagnosis results and the current operating mode to obtain a cleaning prediction result. Based on this cleaning prediction result, the cleaning time point for condenser cleaning can be determined, and based on the fouling diagnosis results, the required cleaning method for condenser cleaning can be determined, thereby generating a condenser cleaning strategy. This allows the condenser cleaning to dynamically adjust the cleaning time and cleaning method according to the amount of fouling and the predicted amount, improving the adaptability and dynamic change capability of condenser cleaning.

[0053] This application's embodiments determine the current operating mode of the condenser and obtain the corresponding modal cleaning recognition model; acquire multi-dimensional data of condenser operation, and perform fouling diagnosis on the multi-dimensional data using the modal cleaning recognition model to obtain fouling diagnosis results; predict the changing trends of the condenser's cleanliness coefficient and vacuum degree based on the fouling diagnosis results and the current operating mode to obtain cleaning prediction results; and generate a condenser cleaning strategy based on the fouling diagnosis results and cleaning prediction results. Because the current operating mode of the condenser is determined, interference caused by operating condition fluctuations can be eliminated, significantly improving the accuracy of fouling diagnosis and enhancing the dynamic tracking capability of fouling diagnosis. Using the modal cleaning recognition model to perform fouling diagnosis on the multi-dimensional data of condenser operation avoids the one-sidedness of single-parameter judgment, enabling timely detection of potential fouling hazards in the early stages of slight performance degradation of the condenser, thus achieving predictive maintenance. By predicting the changing trends of the cleanliness coefficient and vacuum level based on the fouling diagnosis results and the current operating mode, the future operating conditions of the condenser can be predicted, avoiding unnecessary shutdowns caused by fixed-cycle cleaning and emergency shutdowns caused by sudden deterioration of vacuum level. By generating a condenser cleaning strategy based on the fouling diagnosis results and cleaning prediction results, the cleaning time and cleaning method of the condenser can be dynamically adjusted according to the amount of fouling and the predicted amount, thereby improving the adaptability and dynamic change capability of condenser cleaning.

[0054] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating Embodiment 2 of the condenser cleaning strategy management method based on operating modes in this application.

[0055] In the embodiments of this application, such as Figure 2 As shown in the embodiment of this application, the step of predicting the changing trends of the condenser's cleanliness coefficient and vacuum degree based on the fouling diagnosis results and the current operating mode to obtain the cleaning prediction results includes: Step S31: Construct an initial state vector based on the current cleanliness coefficient and current vacuum level corresponding to the dirt diagnosis results; It is understandable that the cleanliness coefficient and vacuum degree corresponding to the above fouling diagnosis results are the current cleaning coefficient and current vacuum degree. Based on the current cleanliness coefficient and current vacuum degree, the initial state vector of the condenser can be constructed.

[0056] It should be understood that the cleanliness coefficient can be used to directly reflect the degree of fouling in the condenser, and the vacuum level can be directly related to the thermal efficiency of the steam turbine and the economics of the unit. Through this initial state vector, both the internal state (degree of fouling) and the external performance (vacuum level) can be captured simultaneously, thus providing a more comprehensive characterization of the condenser's health status.

[0057] Step S32: Determine the prior estimate of the initial state vector at the next moment based on the model parameters corresponding to the current operating mode and the initial state vector; It is understood that the model parameters corresponding to the current operating mode are the model parameters involved in the modal cleaning identification model corresponding to the current operating mode when predicting the trend of change. Specifically, they may include the dirt accumulation rate, vacuum attenuation sensitivity coefficient, etc., and the embodiments of this application do not limit this.

[0058] It should be noted that the above prior estimate is the initial state vector of the next moment predicted based on the initial state vector at the current moment.

[0059] In some embodiments of this application, the model parameters include a dirt accumulation rate and a vacuum decay sensitivity coefficient; the step of determining the prior estimate of the initial state vector at the next moment based on the model parameters corresponding to the current operating mode and the initial state vector includes: obtaining the dirt accumulation rate coefficient and the vacuum decay sensitivity coefficient corresponding to the current operating mode; predicting the cleaning coefficient at the next moment based on the dirt accumulation rate coefficient and the sampling time interval; predicting the vacuum degree at the next moment based on the vacuum decay sensitivity coefficient; and obtaining the prior estimate of the initial state vector at the next moment based on the cleaning coefficient and the vacuum degree at the next moment.

[0060] It is understandable that the above-mentioned fouling accumulation rate coefficient can characterize the amount of fouling growth over time under the current operating mode, and the above-mentioned vacuum degree decay coefficient can characterize the amount of vacuum degree loss due to cleanliness loss under the current operating mode.

[0061] Specifically, the initial state vector of the condenser at the current moment. It can be represented as: ; Where k-1 represents the current time, This indicates the current actual cleanliness level. This indicates the current actual vacuum level.

[0062] It should be noted that, based on the model parameters of the dirt accumulation rate and vacuum decay sensitivity coefficient under the current operating mode, the cleanliness coefficient and vacuum level at the next moment can be predicted. ; ; in, The cleanliness factor for the next time step is predicted based on the current actual cleanliness factor. Indicates the sampling time interval. This represents the fouling accumulation rate coefficient under the current operating mode. This represents the vacuum attenuation sensitivity coefficient under the current operating mode.

[0063] Understandably, based on the cleanliness coefficient and vacuum level of the next time step obtained from the above predictions, the prior estimate of the initial state vector for the next time step can be determined: .

[0064] Step S33: Use the prior estimate as a new initial state vector, and return to the step of determining the prior estimate of the initial state vector at the next moment based on the model parameters corresponding to the current running mode and the initial state vector, until the number of prior estimates obtained is greater than the maximum number of sequences. Step S34: Construct a state vector change trend sequence based on the prior estimates at each time point, and use the state vector change trend sequence as the cleaning prediction result.

[0065] Understandably, by using the prior estimate as the new initial state vector and returning to the step of determining the prior estimate of the initial state vector at the next moment based on the model parameters corresponding to the current operating mode and the initial state vector, the prediction of the initial state vector at each time step can be achieved, thus obtaining the prior estimate of the initial state vector at each time step. Based on these prior estimates of the initial state vectors at these time steps, a sequence of state vector change trends can be constructed. When the number of prior estimates in the state vector change trend sequence exceeds the maximum number of sequences, the iteration process can be stopped, and this state vector change trend sequence can be used as the cleaned prediction result.

[0066] It should be noted that the maximum number of sequences mentioned above can be set based on actual applications, such as 5 or 8, and this application embodiment does not impose any restrictions on this.

[0067] It is understandable that the aforementioned state vector change trend sequence can be used to characterize the change of the condenser's state vector over time. Based on this cleaning prediction result, the cleaning time point can be determined. Specifically, the step of generating a cleaning strategy for the condenser based on the fouling diagnosis result and the cleaning prediction result includes: determining the condenser's cleaning priority based on the threshold range of the fouling diagnosis result; determining the condenser's cleaning method and target cleaning threshold based on the cleaning priority; using the time point corresponding to the prior estimate of reaching the target cleaning threshold in the state vector change trend sequence as the cleaning time point; and generating the condenser's cleaning strategy based on the cleaning method and the cleaning time point.

[0068] It should be noted that the above threshold range can be an interval that distinguishes the current actual cleanliness coefficient and / or the current actual vacuum degree of the dirt diagnosis result. The number of threshold ranges can be multiple, and the embodiments of this application do not limit this.

[0069] In some embodiments of this application, the above threshold range may include: normal operation range (e.g., the current actual cleaning coefficient is not less than 90%), planned maintenance range (e.g., the current actual cleaning coefficient is less than 90% but not less than 80%), early warning maintenance range (e.g., the current actual cleaning coefficient is less than 80% but not less than 70%), and emergency maintenance range (e.g., the current actual cleaning coefficient is less than 70%).

[0070] It is understandable that different threshold intervals correspond to different condenser cleaning priorities, and therefore the corresponding cleaning methods will also be different. For example, in the emergency maintenance interval, the current actual cleanliness coefficient is low, so emergency cleaning with shutdown is required, and the cleaning priority is the highest. In this application embodiment, no restrictions are placed on each threshold interval and its corresponding cleaning priority. The number of threshold intervals, the division method of threshold intervals, and the cleaning priority and cleaning method corresponding to each threshold interval can be set based on the actual application situation.

[0071] It should be noted that the aforementioned target cleaning threshold refers to the cleaning coefficient or vacuum level value that requires cleaning. For example, for threshold ranges with higher cleaning coefficients, the corresponding target cleaning threshold can be set within that range; for instance, the target cleaning threshold for the normal operation zone can be set to 92%. Conversely, for threshold ranges with lower cleaning coefficients, the corresponding target cleaning threshold may not be within that range; for instance, the target cleaning threshold for the emergency maintenance zone can be set to 72%.

[0072] Understandably, the prior estimates in the aforementioned state vector change trend sequence can be arranged in ascending order of time intervals from the current moment. The closer to the current moment, the higher the corresponding cleanliness coefficient and vacuum level; the further away from the current moment, the lower the corresponding cleanliness coefficient and vacuum level. By determining the target cleaning threshold and taking the time point corresponding to the first prior estimate in the state vector change trend sequence that falls below the target cleaning threshold as the cleaning time point, a condenser cleaning strategy can be generated based on the cleaning method and the cleaning time point.

[0073] In some embodiments of this application, the target cleaning threshold can also be a dynamic threshold. Specifically, the step of determining the cleaning method and target cleaning threshold of the condenser based on the cleaning priority includes: determining a cleaning threshold adjustment parameter based on the cleaning priority; determining the cleaning method of the condenser based on the cleaning priority; and dynamically adjusting the current cleanliness coefficient corresponding to the fouling diagnosis result based on the cleaning threshold adjustment parameter to obtain the target cleaning threshold.

[0074] Understandably, different cleaning priorities require different cleaning threshold adjustment parameters. Lower cleaning priorities require lower adjustment parameters, while higher priorities require higher adjustment parameters. This allows for dynamic adjustment of the target cleaning threshold, further preventing under- or over-cleaning caused by fixed cleaning cycles.

[0075] This embodiment constructs an initial state vector based on the current cleanliness coefficient and current vacuum level corresponding to the dirt diagnosis result; determines a priori estimate of the initial state vector for the next moment based on the model parameters corresponding to the current operating mode and the initial state vector; uses the priori estimate as the new initial state vector, and returns to execute the step of determining the priori estimate of the initial state vector for the next moment based on the model parameters corresponding to the current operating mode and the initial state vector, until the number of prior estimates obtained is greater than the maximum number of sequences; constructs a state vector change trend sequence based on the prior estimates at each moment, and uses the state vector change trend sequence as the cleaning prediction result. Since multi-step trend prediction is achieved by determining the prior estimates of the initial state vectors at subsequent moments, it provides a direct basis for subsequent accurate decision-making.

[0076] Based on the first and / or second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to the first and / or second embodiments described above can be referred to the above description and will not be repeated hereafter. Based on this, please refer to... Figure 3 , Figure 3This is a flowchart illustrating Embodiment 3 of the condenser cleaning strategy management method based on operating modes provided in this application.

[0077] In the embodiments of this application, such as Figure 3 As shown, the step of performing dirt diagnosis on the multi-dimensional data using the modal cleaning recognition model to obtain dirt diagnosis results includes: Step S21: Determine the heat transfer coefficient and vacuum degree of the cleaning state corresponding to the modal cleaning identification model. Step S22: Determine the current actual heat transfer coefficient and current actual vacuum degree of the condenser based on the multi-dimensional data; Step S23: Determine the current cleanliness coefficient of the condenser based on the heat transfer coefficient under the clean state and the current actual heat transfer coefficient; Step S24: Determine the current vacuum deviation of the condenser based on the vacuum level under clean conditions and the current actual vacuum level; Step S25: Determine the dirt diagnosis result based on the current cleanliness coefficient and the current vacuum deviation.

[0078] It is understood that the current actual heat transfer coefficient and current actual vacuum level of the condenser can be determined based on multi-dimensional data of the condenser. This application embodiment does not restrict the specific calculation method of the current actual heat transfer coefficient and current actual vacuum level, and can select one according to the needs of actual use. Based on the vacuum level of the clean state corresponding to the current operating mode and the current actual vacuum level during condenser operation, the current vacuum level deviation can be determined, and then the fouling diagnosis result can be determined based on the current cleanliness coefficient and the current vacuum level deviation. Specifically, in this application embodiment, the current cleanliness coefficient and the current vacuum level deviation can be directly used as the fouling diagnosis result.

[0079] In some embodiments of this application, the fouling level can also be classified based on the fouling diagnosis result. Specifically, the classification can be based on the above-mentioned threshold range, or it can be based on other methods, and this application does not limit this.

[0080] This application's embodiments determine the heat transfer coefficient and vacuum level of the condenser in the clean state corresponding to the modal cleaning identification model; determine the current actual heat transfer coefficient and vacuum level of the condenser based on multi-dimensional data; determine the current cleanliness coefficient of the condenser based on the heat transfer coefficient in the clean state and the current actual heat transfer coefficient; determine the current vacuum level deviation of the condenser based on the vacuum level in the clean state and the current actual vacuum level; and determine the fouling diagnosis result based on the current cleanliness coefficient and the current vacuum level deviation. By comprehensively judging the cleanliness coefficient and vacuum level, fouling in the condenser can be detected at a earlier stage, improving the condenser's fouling cleaning capability.

[0081] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the condenser cleaning strategy management method based on operating modes of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0082] This application also provides a condenser cleaning strategy management device based on operating modes. Please refer to [reference needed]. Figure 4 , Figure 4 This is a schematic diagram of the module structure of the condenser cleaning strategy management device based on operating modes according to an embodiment of this application. The condenser cleaning strategy management device based on operating modes includes: The mode management module 10 is used to determine the current operating mode of the condenser and obtain the mode cleaning and identification model corresponding to the current operating mode; The fouling diagnosis module 20 is used to acquire multi-dimensional data of condenser operation and perform fouling diagnosis on the multi-dimensional data through the modal cleaning recognition model to obtain fouling diagnosis results. The cleaning prediction module 30 is used to predict the changing trends of the cleanliness coefficient and vacuum degree of the condenser based on the fouling diagnosis results and the current operating mode, and to obtain the cleaning prediction results. The strategy management module 40 is used to generate a cleaning strategy for the condenser based on the fouling diagnosis results and the cleaning prediction results.

[0083] The condenser cleaning strategy management device based on operating modes provided in this application, employing the condenser cleaning strategy management method based on operating modes in the above embodiments, can solve the technical problem that a fixed condenser cleaning cycle easily leads to over-cleaning or under-cleaning. Compared with the prior art, the beneficial effects of the condenser cleaning strategy management device based on operating modes provided in this application are the same as those of the condenser cleaning strategy management method based on operating modes provided in the above embodiments, and other technical features in the condenser cleaning strategy management device based on operating modes are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0084] This application provides a condenser cleaning strategy management device based on operating modes. The condenser cleaning strategy management device based on operating modes includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the condenser cleaning strategy management method based on operating modes in the above embodiment 1.

[0085] The following is for reference. Figure 5The diagram illustrates a structural schematic of a condenser cleaning strategy management device based on operating mode, suitable for implementing embodiments of this application. The condenser cleaning strategy management device based on operating mode in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The condenser cleaning strategy management device based on operating mode shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0086] like Figure 5 As shown, the condenser cleaning strategy management device based on operating mode may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the condenser cleaning strategy management device based on operating mode. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the condenser cleaning strategy management device based on operating modes to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a condenser cleaning strategy management device based on operating modes with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0087] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0088] The condenser cleaning strategy management device based on operating modes provided in this application, employing the condenser cleaning strategy management method based on operating modes in the above embodiments, can solve the technical problem that a fixed condenser cleaning cycle easily leads to over-cleaning or under-cleaning. Compared with the prior art, the beneficial effects of the condenser cleaning strategy management device based on operating modes provided in this application are the same as those of the condenser cleaning strategy management method based on operating modes provided in the above embodiments, and other technical features in this condenser cleaning strategy management device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0089] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0090] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0091] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the condenser cleaning strategy management method based on operating mode in the above embodiments.

[0092] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0093] The aforementioned computer-readable storage medium may be included in the condenser cleaning strategy management device based on operating mode; or it may exist independently and not assembled into the condenser cleaning strategy management device based on operating mode.

[0094] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the condenser cleaning strategy management device based on operating mode, cause the condenser cleaning strategy management device based on operating mode to: Determine the current operating mode of the condenser and obtain the mode cleaning and identification model corresponding to the current operating mode; Acquire multi-dimensional data of condenser operation, and perform fouling diagnosis on the multi-dimensional data through the modal cleaning recognition model to obtain fouling diagnosis results; Based on the fouling diagnosis results and the current operating mode, the changing trends of the condenser's cleanliness coefficient and vacuum level are predicted to obtain cleaning prediction results; A cleaning strategy for the condenser is generated based on the fouling diagnosis results and the cleaning prediction results.

[0095] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0097] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0098] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described condenser cleaning strategy management method based on operating modes. This solves the technical problem that a fixed condenser cleaning cycle easily leads to over-cleaning or under-cleaning. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the condenser cleaning strategy management method based on operating modes provided in the above embodiments, and will not be repeated here.

[0099] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described condenser cleaning strategy management method based on operating modes.

[0100] The computer program product provided in this application can solve the technical problem that a fixed cleaning cycle for condensers can easily lead to over-cleaning or under-cleaning. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the condenser cleaning strategy management method based on operating modes provided in the above embodiments, and will not be repeated here.

[0101] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A condenser cleaning strategy management method based on operating modes, characterized in that, The method includes: Determine the current operating mode of the condenser and obtain the mode cleaning and identification model corresponding to the current operating mode; Acquire multi-dimensional data of condenser operation, and perform fouling diagnosis on the multi-dimensional data through the modal cleaning recognition model to obtain fouling diagnosis results; Based on the fouling diagnosis results and the current operating mode, the changing trends of the condenser's cleanliness coefficient and vacuum level are predicted to obtain cleaning prediction results; A cleaning strategy for the condenser is generated based on the fouling diagnosis results and the cleaning prediction results.

2. The condenser cleaning strategy management method based on operating modes as described in claim 1, characterized in that, The step of predicting the changing trends of the condenser's cleanliness coefficient and vacuum degree based on the fouling diagnosis results and the current operating mode to obtain the cleaning prediction results includes: An initial state vector is constructed based on the current cleanliness coefficient and current vacuum level corresponding to the dirt diagnosis results; Based on the model parameters corresponding to the current operating mode and the initial state vector, a prior estimate of the initial state vector at the next moment is determined; The prior estimate is used as a new initial state vector, and the process of determining the prior estimate of the initial state vector at the next moment based on the model parameters corresponding to the current running mode and the initial state vector is repeated until the number of prior estimates obtained is greater than the maximum number of sequences. A state vector change trend sequence is constructed based on the prior estimates at each time point, and the state vector change trend sequence is used as the cleaning prediction result.

3. The condenser cleaning strategy management method based on operating modes as described in claim 2, characterized in that, The model parameters include the dirt accumulation rate and the vacuum attenuation sensitivity coefficient; The step of determining the prior estimate of the initial state vector at the next moment based on the model parameters corresponding to the current operating mode and the initial state vector includes: Obtain the fouling accumulation rate coefficient and vacuum attenuation sensitivity coefficient corresponding to the current operating mode; The cleaning factor for the next moment is predicted based on the dirt accumulation rate coefficient and the sampling time interval; Predict the vacuum level at the next moment based on the vacuum level decay sensitivity coefficient; The prior estimate of the initial state vector at the next time step is obtained based on the cleanliness coefficient and the vacuum degree at the next time step.

4. The condenser cleaning strategy management method based on operating modes as described in claim 2, characterized in that, The step of generating a cleaning strategy for the condenser based on the fouling diagnosis results and the cleaning prediction results includes: The cleaning priority of the condenser is determined based on the threshold range of the fouling diagnosis results. The cleaning method and target cleaning threshold of the condenser are determined based on the cleaning priority. The time point corresponding to the prior estimate of the target cleaning threshold in the state vector change trend sequence is taken as the cleaning time point. A cleaning strategy for the condenser is generated based on the cleaning method and the cleaning time point.

5. The condenser cleaning strategy management method based on operating modes as described in claim 4, characterized in that, The step of determining the cleaning method and target cleaning threshold of the condenser based on the cleaning priority includes: The cleaning threshold adjustment parameters are determined based on the cleaning priority. The cleaning method for the condenser is determined based on the cleaning priority; and... The current cleaning coefficient corresponding to the dirt diagnosis result is dynamically adjusted according to the cleaning threshold adjustment parameter to obtain the target cleaning threshold.

6. The condenser cleaning strategy management method based on operating modes as described in claim 1, characterized in that, The step of performing dirt diagnosis on the multi-dimensional data using the modal cleaning recognition model to obtain dirt diagnosis results includes: The heat transfer coefficient and vacuum level of the cleaning state corresponding to the modal cleaning identification model are determined. Based on the multi-dimensional data, the current actual heat transfer coefficient and the current actual vacuum level of the condenser are determined. The current cleanliness coefficient of the condenser is determined based on the heat transfer coefficient under clean conditions and the current actual heat transfer coefficient. The current vacuum deviation of the condenser is determined based on the vacuum level under clean conditions and the current actual vacuum level. The dirt diagnosis result is determined based on the current cleanliness coefficient and the current vacuum deviation.

7. The condenser cleaning strategy management method based on operating modes as described in claim 1, characterized in that, Before the step of obtaining the mode cleaning and recognition model corresponding to the current operating mode, the method further includes: Obtain multi-dimensional historical datasets; Clustering is performed on the multi-dimensional historical dataset to obtain modal data clusters; The heat transfer coefficient and vacuum degree in the clean state of each modal data cluster were determined. Based on the heat transfer coefficient and vacuum degree of the clean state, a modal cleaning identification model is constructed for each modal data cluster.

8. A condenser cleaning strategy management device based on operating modes, characterized in that, The condenser cleaning strategy management device based on operating modes includes: The mode management module is used to determine the current operating mode of the condenser and obtain the mode cleaning and identification model corresponding to the current operating mode; The fouling diagnosis module is used to acquire multi-dimensional data of condenser operation and perform fouling diagnosis on the multi-dimensional data through the modal cleaning recognition model to obtain fouling diagnosis results. The cleaning prediction module is used to predict the changing trends of the cleanliness coefficient and vacuum degree of the condenser based on the fouling diagnosis results and the current operating mode, and to obtain the cleaning prediction results. The strategy management module is used to generate a cleaning strategy for the condenser based on the fouling diagnosis results and the cleaning prediction results.

9. A condenser cleaning strategy management device based on operating modes, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the condenser cleaning strategy management method based on any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the condenser cleaning strategy management method based on any one of claims 1 to 7.

Images