Method and system for determining fouling state in a heat exchanger

Abstract

This application discloses a method and system for determining the fouling state in a heat exchanger. First, the temperature and flow rate of the heat exchanger over a period of time, as well as the baseline total heat transfer coefficient (TTC) under clean conditions, are obtained. Then, based on the temperature and flow rate data, a TTC sequence is determined. Next, combined with the baseline TTC, a fouling thermal resistance sequence is determined, enabling more accurate calculation of the fouling thermal resistance and avoiding errors from monitoring a single parameter. Then, based on the fouling thermal resistance sequence and a prediction model, the time when the fouling thermal resistance reaches a pre-set threshold for cleaning the heat exchanger is predicted, and a maintenance suggestion is generated, instructing the heat exchanger to be cleaned at that time. Thus, through real-time monitoring of the fouling thermal resistance, the subsequent development trend can be detected in the early stages of fouling, achieving a shift from post-treatment to pre-emptive warning, avoiding the drawbacks of regular heat exchanger maintenance, manual experience-based maintenance, or post-treatment maintenance.

Description

Technical Field

[0001] This application relates to the field of coal chemical technology, specifically to a method and system for determining the fouling state in a heat exchanger. Background Technology

[0002] In the coal chemical industry, coal gas-water separation is a crucial step in purifying coal gas. Heat exchangers, used to process coal gas-water mixtures with complex compositions rich in suspended solids, oil, salts, and hardness, are highly susceptible to fouling on the inner walls of the heat exchange tubes. Fouling leads to a significant decrease in heat transfer efficiency, a sharp increase in system energy consumption, and increased fluid pressure drop; in severe cases, it can even cause equipment blockage and production shutdowns.

[0003] In related technologies, heat exchangers in gas-water separation systems are typically managed through regular maintenance, manual experience, or passive maintenance after severe deterioration of heat transfer efficiency.

[0004] Therefore, there is an urgent need for a method to provide real-time, accurate, and early warning of the fouling status in heat exchangers, so as to enable predictive maintenance of heat exchangers and ensure production continuity and economy. Summary of the Invention

[0005] In view of this, this application provides a method and system for determining the state of fouling in a heat exchanger, which can detect the subsequent development trend in the early stage of fouling, realize the transformation from post-treatment to pre-warning, and avoid the drawbacks of regular maintenance, manual experience maintenance or post-treatment of heat exchangers.

[0006] To solve the above problems, the technical solution provided in this application is as follows:

[0007] On one hand, embodiments of this application provide a method for determining the fouling state in a heat exchanger. This method is applied to a shell-and-tube heat exchanger in a coal chemical gas-water separation system. The method includes:

[0008] The system acquires the heat exchanger's operating data over a period of time and the baseline total heat transfer coefficient under clean conditions. The operating data is collected by sensors placed at the inlet and outlet of the heat exchanger's tube side or shell side, and includes temperature and flow rate.

[0009] Based on the working data, determine the overall heat transfer coefficient sequence;

[0010] Based on the overall heat transfer coefficient sequence and the baseline overall heat transfer coefficient, the fouling thermal resistance sequence is determined.

[0011] Based on the fouling thermal resistance sequence and the pre-built prediction model, the time when the fouling thermal resistance reaches the second fouling thermal resistance threshold is predicted. The prediction model is a time series prediction model trained on a historical fouling thermal resistance dataset. The historical fouling thermal resistance dataset includes working data and corresponding fouling thermal resistance over a period of time. The second fouling thermal resistance threshold is used to identify the pre-set fouling thermal resistance threshold for cleaning the heat exchanger.

[0012] Generate maintenance recommendations, which indicate when to clean the heat exchanger.

[0013] As one possible implementation, the method also includes:

[0014] If the fouling thermal resistance reaches the first fouling thermal resistance threshold, or the fouling thermal resistance change rate reaches the first preset rate, a fouling trend monitoring warning will be issued. The first fouling thermal resistance threshold is less than the second fouling thermal resistance threshold.

[0015] If the fouling thermal resistance reaches the second fouling thermal resistance threshold, or the fouling thermal resistance change rate reaches the second preset rate, a heat exchanger maintenance warning will be issued. The second preset rate is greater than the first preset rate.

[0016] If the thermal resistance of the dirt reaches the third thermal resistance threshold, a shutdown cleaning warning will be issued. The third thermal resistance threshold is greater than the second thermal resistance threshold.

[0017] As one possible implementation, the working data includes the working data of the hot-side medium or the working data of the cold-side medium, and the reference total heat transfer coefficient includes the reference total heat transfer coefficient of the hot-side medium or the reference total heat transfer coefficient of the cold-side medium.

[0018] Based on the working data, the overall heat transfer coefficient sequence is determined as follows:

[0019] The overall heat transfer coefficient sequence of the hot-side medium is determined based on the working data of the hot-side medium, or the overall heat transfer coefficient sequence of the cold-side medium is determined based on the working data of the cold-side medium.

[0020] Based on the overall heat transfer coefficient sequence and the baseline overall heat transfer coefficient, the fouling thermal resistance sequence is determined as follows:

[0021] The fouling thermal resistance sequence is determined based on the total heat transfer coefficient sequence of the hot-side medium and the reference total heat transfer coefficient, or the fouling thermal resistance sequence is determined based on the total heat transfer coefficient sequence of the cold-side medium and the reference total heat transfer coefficient.

[0022] As one possible implementation, the method also includes:

[0023] If the temperature change rate at the first moment in the working data is greater than the preset temperature change rate threshold or the flow rate change rate is greater than the preset flow rate change threshold, delete the temperature and flow rate at the first moment to obtain the valid data in the working data.

[0024] Based on the working data, the overall heat transfer coefficient sequence is determined as follows:

[0025] Based on the valid data in the working data, the overall heat transfer coefficient sequence is determined.

[0026] One possible approach to obtaining heat exchanger operating data over a period of time includes:

[0027] Based on the data acquisition frequency, the temperature and flow rate of the heat exchanger are collected to obtain the heat exchanger's operating data.

[0028] As one possible implementation, the method also includes:

[0029] Displays working data, the fouling thermal resistance sequence, and the moment when the fouling thermal resistance reaches the second fouling thermal resistance threshold.

[0030] In another aspect, embodiments of this application provide a system for determining the fouling state in a heat exchanger. This system is applied to a shell-and-tube heat exchanger in a coal chemical gas-water separation system. The system includes:

[0031] The acquisition unit is used to acquire the heat exchanger's operating data over a period of time and the baseline total heat transfer coefficient under clean conditions. The operating data is collected by sensors arranged at the inlet and outlet of the heat exchanger's tube side or shell side, and includes temperature and flow rate.

[0032] The determination unit is used to determine the overall heat transfer coefficient sequence based on the working data;

[0033] The determination unit is also used to determine the fouling thermal resistance sequence based on the overall heat transfer coefficient sequence and the reference overall heat transfer coefficient.

[0034] The prediction unit is used to predict the time when the fouling thermal resistance reaches the second fouling thermal resistance threshold based on the fouling thermal resistance sequence and the pre-built prediction model. The prediction model is a time series prediction model trained based on the historical fouling thermal resistance dataset. The historical fouling thermal resistance dataset includes working data and corresponding fouling thermal resistance over a period of time. The second fouling thermal resistance threshold is used to identify the pre-set fouling thermal resistance threshold for cleaning the heat exchanger.

[0035] The generation unit is used to generate maintenance recommendations, which indicate when the heat exchanger should be cleaned.

[0036] As one possible implementation, the system also includes an early warning unit for:

[0037] If the fouling thermal resistance reaches the first fouling thermal resistance threshold, or the fouling thermal resistance change rate reaches the first preset rate, a fouling trend monitoring warning will be issued. The first fouling thermal resistance threshold is less than the second fouling thermal resistance threshold.

[0038] If the fouling thermal resistance reaches the second fouling thermal resistance threshold, or the fouling thermal resistance change rate reaches the second preset rate, a heat exchanger maintenance warning will be issued. The second preset rate is greater than the first preset rate.

[0039] If the thermal resistance of the dirt reaches the third thermal resistance threshold, a shutdown cleaning warning will be issued. The third thermal resistance threshold is greater than the second thermal resistance threshold.

[0040] As one possible implementation, the working data includes the working data of the hot-side medium or the working data of the cold-side medium, and the reference total heat transfer coefficient includes the reference total heat transfer coefficient of the hot-side medium or the reference total heat transfer coefficient of the cold-side medium.

[0041] The determining unit is specifically used to determine the total heat transfer coefficient sequence of the hot-side medium based on the working data of the hot-side medium, or to determine the total heat transfer coefficient sequence of the cold-side medium based on the working data of the cold-side medium.

[0042] The fouling thermal resistance sequence is determined based on the total heat transfer coefficient sequence of the hot-side medium and the reference total heat transfer coefficient, or the fouling thermal resistance sequence is determined based on the total heat transfer coefficient sequence of the cold-side medium and the reference total heat transfer coefficient.

[0043] As one possible implementation, the system also includes a filtering unit for:

[0044] If the temperature change rate at the first moment in the working data is greater than the preset temperature change rate threshold or the flow rate change rate is greater than the preset flow rate change threshold, delete the temperature and flow rate at the first moment to obtain the valid data in the working data.

[0045] The determination unit is specifically used to determine the overall heat transfer coefficient sequence based on the effective data in the working data.

[0046] As one possible implementation, the acquisition unit is specifically used to collect the temperature and flow rate of the heat exchanger based on the data acquisition frequency, so as to obtain the working data of the heat exchanger.

[0047] As one possible implementation, the system also includes a display unit for displaying working data, the fouling thermal resistance sequence, and the moment when the fouling thermal resistance reaches the second fouling thermal resistance threshold.

[0048] In another aspect, this application provides a computer device, which includes a processor and a memory:

[0049] Memory is used to store computer programs;

[0050] The processor is used to execute any of the above methods according to a computer program.

[0051] In another aspect, this application provides a computer-readable storage medium for storing a computer program that, when executed by a computer device, implements the method of performing any of the above-mentioned methods.

[0052] In another aspect, this application provides a computer program product including a computer program, which, when run on a computer device, causes the computer device to perform any of the methods described above.

[0053] As can be seen from the above technical solution, this solution first obtains the temperature and flow rate of the heat exchanger over a period of time, as well as the baseline total heat transfer coefficient under clean conditions. Then, based on the temperature and flow rate data, it determines the total heat transfer coefficient sequence over this period of time. Then, combined with the baseline total heat transfer coefficient, it determines the fouling thermal resistance sequence over this period of time. Furthermore, by combining temperature and flow rate and introducing the baseline total heat transfer coefficient under clean conditions, it is possible to calculate the fouling thermal resistance more accurately, avoiding the error of monitoring a single parameter. Subsequently, based on the fouling thermal resistance sequence and the prediction model, it predicts the time when the fouling thermal resistance reaches the second fouling thermal resistance threshold, that is, the pre-set fouling thermal resistance threshold for cleaning the heat exchanger, and generates maintenance suggestions, indicating that the heat exchanger should be cleaned at that time. Thus, by monitoring the fouling thermal resistance in real time, it is possible to detect the subsequent development trend in the early stage of fouling, realizing the transformation from post-treatment to pre-warning, avoiding the drawbacks of regular heat exchanger maintenance, manual experience maintenance, or post-treatment maintenance. Moreover, the prediction model is a time series prediction model trained based on historical working data and corresponding fouling thermal resistance over a period of time, making the prediction results more accurate and reliable. Attached Figure Description

[0054] 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, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 One of the flowcharts illustrating a method for determining the fouling state in a heat exchanger, provided in an embodiment of this application;

[0056] Figure 2 A second schematic flowchart illustrating a method for determining the fouling state in a heat exchanger, provided in an embodiment of this application;

[0057] Figure 3 A system architecture diagram provided for an embodiment of this application;

[0058] Figure 4A predicted graph of fouling thermal resistance provided for an embodiment of this application;

[0059] Figure 5 This is a schematic diagram of a system for determining the fouling state in a heat exchanger, provided as an embodiment of this application. Detailed Implementation

[0060] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0061] As described in the background section, the methods for determining the fouling state in heat exchangers in related technologies have the following problems:

[0062] (1) Lag: It relies on regular shutdown for maintenance or cleaning until the heat transfer efficiency deteriorates severely and affects production. It cannot achieve early warning, resulting in unplanned shutdowns and huge economic losses.

[0063] (2) Reliance on experience: Maintenance decisions are mostly based on the experience of operators or fixed time cycles, lacking scientific data support, which may lead to over-maintenance or under-maintenance.

[0064] (3) The singleness of the judgment factors: Some existing monitoring methods may only focus on the change of a single parameter such as temperature or pressure, which cannot comprehensively and accurately reflect the overall state of dirt, are easily affected by fluctuations in operating conditions, and have a high false alarm rate.

[0065] Therefore, there is an urgent need for a method to provide real-time, accurate, and early warning of the fouling status in heat exchangers, so as to enable predictive maintenance of heat exchangers and ensure production continuity and economy.

[0066] This application provides a method for determining the fouling state in a heat exchanger. First, the temperature and flow rate of the heat exchanger over a period of time, along with the baseline total heat transfer coefficient (TTC) under clean conditions, are obtained. Then, based on the temperature and flow rate data, a TTC sequence is determined over this period. Next, combined with the baseline TTC, a fouling thermal resistance sequence is determined over this period. Furthermore, by combining temperature and flow rate data and incorporating the baseline TTC under clean conditions, the fouling thermal resistance can be calculated more accurately, avoiding errors from single-parameter monitoring. Then, based on the fouling thermal resistance sequence and a prediction model, the method predicts when the fouling thermal resistance will reach a second fouling thermal resistance threshold—a pre-set threshold for clearly defining the fouling thermal resistance of the heat exchanger—and generates maintenance recommendations instructing the heat exchanger to be cleaned at that moment. Through real-time monitoring of the fouling thermal resistance, the method can detect subsequent trends in the early stages of fouling, shifting from reactive to proactive management. This avoids the drawbacks of periodic heat exchanger maintenance, manual experience-based maintenance, or reactive maintenance. Moreover, the prediction model is a time-series prediction model trained based on historical operating data and corresponding fouling thermal resistance data, making the prediction results more accurate and reliable.

[0067] The solutions provided in this application relate to the field of coal chemical technology, and are specifically illustrated through the following embodiments.

[0068] See Figure 1 The diagram shown is one of the flowcharts illustrating a method for determining the fouling state in a heat exchanger according to an embodiment of this application. This method is applied to a shell-and-tube heat exchanger in a coal chemical gas-water separation system, including steps S101-S105.

[0069] S101: Obtain the operating data of the heat exchanger over a period of time and the baseline total heat transfer coefficient under clean conditions.

[0070] The working data includes temperature and flow rate. This data is collected by sensors placed at the inlet and outlet of the heat exchanger's tube or shell side. For example, installing a Pt100 platinum resistance thermometer (4-wire system) on the straight pipe sections of the heat exchanger's inlet and outlet pipes ensures high accuracy and stability of the temperature measured at the measurement points. Depending on the medium characteristics, electromagnetic flowmeters or vortex flowmeters are selected and installed in the stable flow field region at the heat exchanger's inlet or outlet.

[0071] The overall heat transfer coefficient is used to indicate the ability to transfer heat per unit area and per unit temperature difference. The more fouling inside the heat exchanger, the smaller the overall heat transfer coefficient. Therefore, the overall heat transfer coefficient can be used to determine the fouling status of the heat exchanger.

[0072] The baseline total heat transfer coefficient refers to the total heat transfer coefficient of the heat exchanger in a clean state. For example, it can be obtained based on the data of the heat exchanger's initial operation or from a historical database. This application does not impose specific limitations on this.

[0073] One possible approach is to collect the temperature and flow rate of the heat exchanger based on the data acquisition frequency to obtain the heat exchanger's operating data.

[0074] The data acquisition frequency refers to the frequency of data acquisition. This application does not impose specific limitations on this frequency. For example, it can be a pre-set fixed time interval or a time interval based on the dynamic changes in the working status of the gas-water separation system.

[0075] Therefore, by controlling the data acquisition frequency, the data acquisition cycle can be controlled, thereby reducing the data acquisition frequency and lowering the system load when the gas-water separation system is in a stable state.

[0076] In addition, differential pressure data of the heat exchanger can be collected. For example, a high-precision differential pressure transmitter can be used to obtain the differential pressure data of the inlet and outlet of the hot and cold sides of the heat exchanger, and calculate the differential pressure relative to the early cleaning state of the heat exchanger, or the differential pressure change rate relative to the differential pressure change rate corresponding to the cleaning state, so as to assist the system in judging the fouling status.

[0077] S102: Determine the overall heat transfer coefficient sequence based on the working data.

[0078] The total heat transfer coefficient sequence includes the total heat transfer coefficients at each time point within this time period.

[0079] For example, the overall heat transfer coefficient can be calculated based on the fundamental equations of heat transfer. The fundamental equations of heat transfer are as follows:

[0080] (Formula 1)

[0081] Where K represents the overall heat transfer coefficient and A represents the rated heat transfer area. Let Q represent the logarithmic mean temperature difference, and Q be the heat transfer. The heat transfer Q can be calculated using the following formula:

[0082] (Formula 2)

[0083] Where M is the flow rate and Cp is the specific heat capacity of the medium. This refers to the inlet temperature of the heat exchanger. This is the outlet temperature of the heat exchanger.

[0084] Furthermore, based on the overall heat transfer coefficient sequence and the baseline overall heat transfer coefficient sequence, it is helpful to determine the degree of fouling in the heat exchanger.

[0085] S103: Determine the fouling thermal resistance sequence based on the overall heat transfer coefficient sequence and the reference overall heat transfer coefficient.

[0086] The fouling thermal resistance sequence includes the fouling thermal resistance at each moment within this time period. Fouling thermal resistance refers to the additional thermal resistance caused by fouling on heat transfer.

[0087] For example, the fouling thermal resistance Rf can be calculated based on the formula:

[0088] (Formula 3)

[0089] Where K refers to the overall heat transfer coefficient and Kclean refers to the baseline overall heat transfer coefficient. It should be noted that K and Kclean must be calculated based on the same heat transfer area.

[0090] Furthermore, based on the total heat transfer coefficient at each time point, the fouling thermal resistance at each time point can be determined, thus obtaining the fouling thermal resistance sequence.

[0091] S104: Based on the fouling thermal resistance sequence and a pre-built prediction model, predict the moment when the fouling thermal resistance reaches the second fouling thermal resistance threshold.

[0092] The second fouling thermal resistance threshold is used to identify a pre-set fouling thermal resistance threshold for cleaning the heat exchanger. This application does not impose specific limitations on this; for example, the second fouling thermal resistance threshold can be set to 0.0007.

[0093] The prediction model is a time series prediction model trained on a historical fouling thermal resistance dataset. The historical fouling thermal resistance dataset includes working data and corresponding fouling thermal resistance over a period of time, and may also include operating condition parameters such as pressure difference. Supervised training of the time series prediction model based on the fouling thermal resistance dataset can effectively improve prediction accuracy.

[0094] The embodiments of this application do not impose specific limitations on the prediction model. For example, it can be based on time series, such as long short-term memory networks, which have captured time-series dependency information.

[0095] By inputting the fouling thermal resistance sequence into the prediction model, the fouling thermal resistance in the future can be predicted, thereby determining the specific time when the fouling thermal resistance reaches the second fouling thermal resistance threshold, and determining when the heat exchanger needs to be cleaned.

[0096] S105: Generate maintenance recommendations.

[0097] The maintenance recommendations are used to indicate when the heat exchanger should be cleaned.

[0098] This application does not impose specific restrictions on the method of generating maintenance suggestions. For example, code can be written to generate "Please clean the heat exchanger in time before XX" to remind operators to manage the heat exchanger in advance.

[0099] Therefore, this application obtains the temperature and flow rate of the heat exchanger over a period of time, as well as the baseline total heat transfer coefficient under clean conditions. Then, based on the temperature and flow rate data, it determines the total heat transfer coefficient sequence over this period of time. Then, combined with the baseline total heat transfer coefficient, it determines the fouling thermal resistance sequence over this period of time. Furthermore, by combining temperature and flow rate and introducing the baseline total heat transfer coefficient under clean conditions, it is possible to calculate the fouling thermal resistance more accurately, avoiding the errors of single parameter monitoring. Subsequently, based on the fouling thermal resistance sequence and the prediction model, it predicts the time when the fouling thermal resistance reaches the second fouling thermal resistance threshold, that is, the pre-set time when the heat exchanger will reach the clear fouling thermal resistance threshold, and generates maintenance suggestions, indicating that the heat exchanger should be cleaned at that time. Thus, by monitoring the fouling thermal resistance in real time, it is possible to discover the subsequent development trend in the early stage of fouling, realizing the transformation from post-treatment to pre-warning, avoiding the drawbacks of regular heat exchanger maintenance, manual experience maintenance, or post-treatment maintenance. Moreover, the prediction model is a time series prediction model trained based on historical working data and corresponding fouling thermal resistance over a period of time, making the prediction results more accurate and reliable.

[0100] As one possible implementation, the method also includes:

[0101] A1: If the thermal resistance of the dirt reaches the first thermal resistance threshold, or the rate of change of the thermal resistance of the dirt reaches the first preset rate, a dirt trend monitoring warning will be issued.

[0102] A2: If the fouling thermal resistance reaches the second fouling thermal resistance threshold, or the fouling thermal resistance change rate reaches the second preset rate, a heat exchanger maintenance warning will be issued.

[0103] A3: If the thermal resistance of the dirt reaches the third thermal resistance threshold, a shutdown cleaning warning will be issued.

[0104] The first fouling thermal resistance threshold refers to a preset fouling thermal resistance threshold, which is less than the second fouling thermal resistance threshold. For example, if the second fouling thermal resistance threshold is 0.0007, the first fouling thermal resistance threshold can be set to 0.0003.

[0105] The rate of change of fouling thermal resistance refers to the rate at which the thermal resistance of fouling changes.

[0106] The first preset rate refers to a pre-set threshold for the rate of change of fouling thermal resistance, and this application embodiment does not impose specific limitations on it.

[0107] The second preset rate refers to a pre-set threshold for the rate of change of fouling thermal resistance, which is greater than the first preset rate.

[0108] The third fouling thermal resistance threshold refers to a pre-set fouling thermal resistance threshold, which is greater than the second fouling thermal resistance threshold. For example, if the second fouling thermal resistance threshold is 0.0007, the third fouling thermal resistance threshold can be set to 0.0009.

[0109] When the fouling thermal resistance reaches the first fouling thermal resistance threshold, or the fouling threshold change rate reaches the first preset rate, it is considered that the fouling in the heat exchanger has accumulated to a certain extent and its state may change abruptly at any time. Therefore, a fouling trend detection warning needs to be issued so that the operator can monitor the change trend of the fouling in real time, and can promptly detect and perform corresponding maintenance on the heat exchanger when the state of the fouling changes abruptly.

[0110] When the fouling thermal resistance reaches the second fouling thermal resistance threshold, or the fouling threshold change rate reaches the second preset rate, it is considered that the fouling in the heat exchanger will have a significant impact on the normal operation of the heat exchanger, and a heat exchanger maintenance warning is issued to remind the operator to clean the heat exchanger in a timely manner.

[0111] When the fouling thermal resistance reaches the third fouling thermal resistance threshold, it is considered that the fouling inside the heat exchanger is seriously affecting the operation of the heat exchanger. In this case, a statistical cleaning warning needs to be issued to prompt the operator to stop the machine immediately for cleaning of the heat exchanger.

[0112] Therefore, by introducing the fouling thermal resistance change rate on the basis of fouling thermal resistance, we can see the accelerating trend of fouling and more accurately reflect the fouling status in the heat exchanger. Furthermore, by combining a multi-level early warning mechanism, when the fouling status is determined to reach a certain level based on the fouling thermal resistance or the fouling thermal resistance change rate, the corresponding level of early warning can be issued in a timely manner. This makes the alarm information more instructive and facilitates decision-making and resource allocation by operators.

[0113] As one possible implementation, if the working data includes working data for the hot-side medium or the cold-side medium, then the following steps are performed:

[0114] B1: Determine the total heat transfer coefficient sequence of the hot-side medium based on the working data of the hot-side medium, or determine the total heat transfer coefficient sequence of the cold-side medium based on the working data of the cold-side medium.

[0115] B2: Determine the fouling thermal resistance sequence based on the total heat transfer coefficient sequence of the hot-side medium and the reference total heat transfer coefficient, or determine the fouling thermal resistance sequence based on the total heat transfer coefficient sequence of the cold-side medium and the reference total heat transfer coefficient.

[0116] For example, based on the flow rate M1 of the hot-side medium, the specific heat capacity Cp1 of the hot-side medium, and the inlet temperature... outlet temperature ,pass The heat transfer capacity Q of the hot-side medium is calculated, and then based on Q= The overall heat transfer coefficient K is calculated, where A1 is the heat transfer area of ​​the hot-side medium. Then, based on the overall heat transfer coefficient K of the hot-side medium and the corresponding reference overall heat transfer coefficient Kclean (i.e., the heat transfer area is the same when solving K and Kclean based on the basic equation of heat transfer), the fouling thermal resistance is determined by formula 3.

[0117] Alternatively, it can be based on the flow rate M2 of the cold-side medium, the specific heat capacity Cp2 of the cold-side medium, and the inlet temperature. and outlet temperature ,pass The heat transfer Q2 of the cold-side medium is calculated, and then based on Q2= The overall heat transfer coefficient K is calculated, where A2 is the heat transfer area of ​​the cold-side medium. Then, based on the overall heat transfer coefficient K of the cold-side medium and the corresponding reference overall heat transfer coefficient Kclean (i.e., the heat transfer area is the same when solving for K and Kclean based on the basic heat transfer equation), the fouling thermal resistance is determined by Equation 3.

[0118] Therefore, the fouling thermal resistance can be calculated based on the working data obtained from the cold side medium or the hot side medium. This avoids the situation where the fouling thermal resistance cannot be calculated due to the failure of a single sensor when the sensor at part of the cold side medium or the hot side medium fails, thus helping to improve the stability and effectiveness of the gas-water separation system.

[0119] As one possible implementation, the method also includes:

[0120] If the temperature change rate at the first moment in the working data is greater than the preset temperature change rate threshold or the flow rate change rate is greater than the preset flow rate change threshold, delete the temperature and flow rate at the first moment to obtain the valid data in the working data.

[0121] S102 includes:

[0122] Based on the valid data in the working data, the overall heat transfer coefficient sequence is determined.

[0123] Among them, the rate of temperature change refers to the rate of temperature change, and the rate of flow rate change refers to the rate of flow rate change.

[0124] The preset temperature change rate threshold refers to a pre-set temperature change rate threshold, and the preset flow rate change rate threshold refers to a pre-set flow rate change rate threshold. This application does not impose specific limitations on these. For example, the preset temperature change rate threshold can be determined based on the temperature change rate of the heat exchanger over a historical period, and the preset flow rate change rate threshold can be determined based on the flow rate change rate over a historical period.

[0125] After obtaining the working data, it is necessary to preprocess the data, such as removing outliers, filtering and smoothing, and eliminating noise.

[0126] For example, if the rate of change of temperature at the first moment in the working data is greater than the corresponding preset threshold, or the rate of change of flow rate is greater than the corresponding preset threshold, the system is considered unstable. At this time, the corresponding working data is abnormal data. The temperature and flow rate at the first moment are deleted, and the remaining working data is taken as valid data. Then, the total heat transfer coefficient sequence is determined based on the valid data. This total heat transfer coefficient sequence does not include the total heat transfer coefficient corresponding to the first moment.

[0127] Therefore, based on the rate of change of temperature or the rate of change of flow, it can be determined whether the collected data is abnormal. When the rate of change of temperature or the rate of change of flow exceeds a preset threshold, it is considered abnormal data and deleted. Then, subsequent operations can be carried out based on more accurate working data, which can effectively improve the accuracy of prediction results.

[0128] As one possible implementation, the method also includes:

[0129] Displays working data, the fouling thermal resistance sequence, and the moment when the fouling thermal resistance reaches the second fouling thermal resistance threshold.

[0130] The system's front-end interface displays the fouling thermal resistance sequence corresponding to working data over a period of time, as well as the predicted moment when the fouling thermal resistance reaches the second fouling thermal resistance threshold.

[0131] Therefore, the content displayed on the front end can help operators perform real-time monitoring and thus perform heat exchanger maintenance in advance.

[0132] To more clearly describe the method for determining the fouling state in this type of heat exchanger, the following explanation is provided in conjunction with a specific implementation scenario.

[0133] See Figure 2 The diagram shown is a second flowchart illustrating a method for determining the fouling state in a heat exchanger according to an embodiment of this application. First, the temperature, flow rate, and pressure difference inside the heat exchanger are acquired through a data acquisition layer to obtain real-time operating data. Then, the total heat transfer coefficient is calculated based on the operating data. Subsequently, core state indicators, such as fouling thermal resistance and the rate of change of fouling thermal resistance, are calculated by combining the baseline total heat transfer coefficient sequence of the heat exchanger in a clean state and the rate of change of pressure difference. Then, based on the real-time fouling thermal resistance and the rate of change of fouling thermal resistance, combined with multi-level early warning rules, the fouling thermal resistance in the future is predicted, maintenance suggestions and alarms are generated, and maintenance suggestions and alarms are output.

[0134] See Figure 3 The diagram shown is a system architecture diagram provided in an embodiment of this application, including a perception and data acquisition layer, an analysis and calculation layer, and an application and display layer. The composition and function of each layer are described below by way of example.

[0135] (1) Sensing and data acquisition layer (hardware foundation).

[0136] a. Sensor selection and installation, installed in the heat exchanger system piping.

[0137] Temperature sensor: Utilizing a Pt100 platinum resistance thermometer (4-wire system), offering high accuracy and stability. Installed on straight pipe sections of the heat exchanger inlet and outlet pipelines to ensure sufficient fluid flow at the measurement point.

[0138] Flow sensor: Depending on the characteristics of the medium, an electromagnetic flow meter or a vortex flow meter is selected. It is installed in the stable flow field region at the inlet or outlet of the heat exchanger.

[0139] Differential pressure sensor: A high-precision differential pressure transmitter is selected, with pressure taps located at the inlet and outlet of the heat exchanger on the hot and cold sides, respectively.

[0140] Water quality analyzer: Install an online turbidity meter, online oil content analyzer, or online hardness meter on the upstream pipeline of the heat exchanger to provide auxiliary data for fouling type analysis and root cause determination.

[0141] b. Data acquisition and transmission.

[0142] Hardware: Uses an industrial programmable logic controller (PLC) or remote read / write (IO) module, equipped with an analog input module to receive 4-20mA or HART signals from the sensor.

[0143] Network: Real-time data streams collected by PLC / IO modules are transmitted to the real-time database of the distributed control system (DCS) or data acquisition and monitoring control system (SCADA) in the central control room via fieldbuses such as industrial Ethernet or PROFIBUS-DP.

[0144] Requirements: Ensure the frequency and stability of data acquisition; scan cycle ≤ 1 second.

[0145] (2) Analysis and Computation Layer. This layer is responsible for transforming working data into valuable metric data. This layer is typically deployed on a real-time database or a dedicated industrial data platform / edge computing gateway.

[0146] a. Data preprocessing module.

[0147] Data cleaning: Remove outliers and smooth the working data to eliminate measurement noise.

[0148] Operating condition assessment: Identifies whether the system is in a stable operating condition. Subsequent calculations are only performed when the flow rate and inlet temperature fluctuations are less than the set thresholds to ensure the accuracy of the calculation results. If the fluctuations are too large, the calculation is paused or a dynamic compensation algorithm is used.

[0149] b. Core model calculation module.

[0150] Real-time overall heat transfer coefficient (K) calculation engine: Reads temperature and flow rate in real time, obtains the specific heat capacity Cp of the medium from the physical property parameter library (or simplified formula); calculates the heat transfer Q and logarithmic mean temperature difference. ; Execute formula The overall heat transfer coefficient K is calculated.

[0151] Real-time fouling thermal resistance (Rf) calculation engine: calls the pre-stored Kclean baseline value from the system configuration; executes the formula Rf = 1 / K - 1 / Kclean.

[0152] Differential Pressure Change Rate Calculation Engine: Calculates the ratio or absolute difference between the current differential pressure and the clean baseline differential pressure.

[0153] c. Intelligent early warning and prediction module.

[0154] Dynamic threshold management: Administrators can configure thresholds for multi-level warnings (e.g., first dirt thermal resistance threshold = 0.0003, second dirt thermal resistance threshold = 0.0007) and first and second preset rates in the interface.

[0155] d. Predictive models.

[0156] Data storage: The calculated Rf sequence data is stored in a time series database;

[0157] Model Deployment: Integrate a lightweight machine learning runtime environment (such as Python ONNX Runtime). Deploy trained prediction models (such as ARIMA, LSTM) here;

[0158] Regular prediction: The system automatically runs a prediction once a day, takes the Rf sequence data of the past N days as input, outputs the time point in the next M days when Rf will reach the second fouling thermal resistance threshold, and updates the prediction results.

[0159] (3) Application and presentation layer (user interface).

[0160] This layer serves as the window for system-user interaction, typically achieved through a Human-Machine Interface (HMI). The front end is presented as a Web configuration interface or a screen showing the addition of new functions to the SCADA system.

[0161] a. Real-time monitoring panel.

[0162] Flowchart: The heat exchanger is displayed in the form of a process flow diagram, with key data (temperature, flow rate, K value, Rf value) displayed in real time at the corresponding locations.

[0163] Key Performance Indicator (KPI) Dashboard: Prominently displays the current system status (normal / early warning / alarm), current Rf value, and number of days until the predicted cleaning time.

[0164] b. Trend analysis.

[0165] Provides multivariate trend graphs that simultaneously display the curves of Rf, K value, and pressure difference over time, clearly showing their correlation and trends. See also Figure 4 The figure shown is a prediction graph of fouling thermal resistance provided in an embodiment of this application. The graph displays the predicted values ​​of fouling thermal resistance during the 0-100 days of heat exchanger operation, where the first preset threshold is... The second fouling thermal resistance threshold is .

[0166] c. Alarm Center.

[0167] When an alert is triggered, the interface will show a clear color change (such as flashing yellow or a red alert).

[0168] A pop-up alarm list records the alarm time, level, description, and confirmation status in detail.

[0169] It supports integration with sound and light alarm systems and SMS / WeChat push platforms to ensure that information is delivered to the responsible person in a timely manner.

[0170] d. Forecast report.

[0171] Provides flexible historical data query and export functions;

[0172] It automatically generates dirt trend analysis reports and maintenance suggestion reports, providing data support for equipment management.

[0173] An example of how to create this system is as follows:

[0174] Phase 1: Feasibility verification.

[0175] Add necessary sensors to the existing DCS / SCADA system;

[0176] Using historical data, the K and Rf values ​​were manually calculated to verify the correlation between this indicator and the on-site dirt conditions.

[0177] Determine the baseline value for Kclean.

[0178] Phase Two: Core System Development.

[0179] Develop data preprocessing modules and K-value and Rf-value calculation modules on real-time databases or edge computing platforms;

[0180] Develop preliminary monitoring screens and simple threshold alarms on the SCADA system;

[0181] Phase 3: Intelligent Upgrade.

[0182] Introducing fouling thermal resistance change rate analysis and multi-level early warning logic;

[0183] Collect sufficient historical working data to train and deploy the predictive model;

[0184] Develop a complete predictive maintenance decision support interface.

[0185] Phase 4: System Integration and Optimization.

[0186] Integrate this system with the enterprise's existing enterprise asset management system or work order system to enable automatic triggering of maintenance work orders based on early warning information;

[0187] Continuously optimize model parameters and early warning rules.

[0188] Based on the above embodiments, this application provides a system for determining the fouling state in a heat exchanger. This system is applied to a shell-and-tube heat exchanger in a coal chemical gas-water separation system. (Refer to...) Figure 5 The diagram shown is a schematic 500 of a system for determining the fouling state in a heat exchanger according to an embodiment of this application. The system includes:

[0189] The acquisition unit 501 is used to acquire the operating data of the heat exchanger over a period of time and the reference total heat transfer coefficient under clean conditions. The operating data is collected by sensors arranged at the inlet and outlet of the tube side or shell side of the heat exchanger. The operating data includes temperature and flow rate.

[0190] The determining unit 502 is used to determine the overall heat transfer coefficient sequence based on the working data;

[0191] The determining unit 502 is further configured to determine a fouling thermal resistance sequence based on the total heat transfer coefficient sequence and the reference total heat transfer coefficient.

[0192] The prediction unit 503 is used to predict the time when the fouling thermal resistance reaches the second fouling thermal resistance threshold based on the fouling thermal resistance sequence and the pre-built prediction model. The prediction model is a time series prediction model trained based on a historical fouling thermal resistance dataset. The historical fouling thermal resistance dataset includes the working data and the corresponding fouling thermal resistance over a historical period. The second fouling thermal resistance threshold is used to identify the pre-set fouling thermal resistance threshold for cleaning the heat exchanger.

[0193] The generation unit 504 is used to generate a maintenance recommendation, which indicates that the heat exchanger should be cleaned at the specified time.

[0194] As one possible implementation, the system also includes an early warning unit for:

[0195] If the fouling thermal resistance reaches the first fouling thermal resistance threshold, or the fouling thermal resistance change rate reaches the first preset rate, a fouling trend monitoring warning is issued, wherein the first fouling thermal resistance threshold is less than the second fouling thermal resistance threshold.

[0196] If the fouling thermal resistance reaches the second fouling thermal resistance threshold, or the fouling thermal resistance change rate reaches the second preset rate, a heat exchanger maintenance warning is issued, wherein the second preset rate is greater than the first preset rate.

[0197] If the thermal resistance of the dirt reaches the third thermal resistance threshold, a shutdown cleaning warning will be issued, wherein the third thermal resistance threshold is greater than the second thermal resistance threshold.

[0198] As one possible implementation, the working data includes the working data of the hot-side medium or the working data of the cold-side medium, and the reference total heat transfer coefficient includes the reference total heat transfer coefficient of the hot-side medium or the reference total heat transfer coefficient of the cold-side medium.

[0199] The determining unit is specifically used to determine the total heat transfer coefficient sequence of the hot-side medium based on the working data of the hot-side medium, or to determine the total heat transfer coefficient sequence of the cold-side medium based on the working data of the cold-side medium.

[0200] A fouling thermal resistance sequence is determined based on the total heat transfer coefficient sequence of the hot-side medium and the reference total heat transfer coefficient, or a fouling thermal resistance sequence is determined based on the total heat transfer coefficient sequence of the cold-side medium and the reference total heat transfer coefficient.

[0201] As one possible implementation, the system further includes a filtering unit for:

[0202] If the temperature change rate at the first moment in the working data is greater than a preset temperature change rate threshold or the flow rate change rate is greater than a preset flow rate change rate threshold, then the temperature and flow rate at the first moment are deleted to obtain the valid data in the working data.

[0203] The determining unit is specifically used to determine the overall heat transfer coefficient sequence based on the valid data in the working data.

[0204] As one possible implementation, the acquisition unit is specifically used to acquire the temperature and flow rate of the heat exchanger based on the data acquisition frequency, so as to obtain the operating data of the heat exchanger.

[0205] As one possible implementation, the system further includes a display unit for displaying the operating data, the fouling thermal resistance sequence, and the moment when the fouling thermal resistance reaches the second fouling thermal resistance threshold.

[0206] Based on the above embodiments, this application provides a computer device, which includes a processor and a memory:

[0207] The memory is used to store computer programs;

[0208] The processor is used to execute the method for determining the fouling state in the heat exchanger according to the computer program.

[0209] Based on the above embodiments, this application provides a computer-readable storage medium for storing a computer program, which, when executed by a computer device, implements the method for determining the fouling state in the heat exchanger.

[0210] Based on the above embodiments, this application provides a computer program product including a computer program, which, when run on a computer device, causes the computer device to execute the above-described method for determining the fouling state in the heat exchanger.

[0211] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0212] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining the fouling state in a heat exchanger, characterized in that, The method is applied to a shell-and-tube heat exchanger in a coal chemical gas-water separation system. The method includes: The heat exchanger's operating data over a period of time and its baseline total heat transfer coefficient under clean conditions are obtained. The operating data is collected by sensors located at the inlet and outlet of the heat exchanger's tube side or shell side, and includes temperature and flow rate. Based on the aforementioned working data, a sequence of overall heat transfer coefficients is determined; Based on the total heat transfer coefficient sequence and the reference total heat transfer coefficient, the fouling thermal resistance sequence is determined; Based on the fouling thermal resistance sequence and the pre-built prediction model, the time when the fouling thermal resistance reaches the second fouling thermal resistance threshold is predicted. The prediction model is a time series prediction model trained based on a historical fouling thermal resistance dataset. The historical fouling thermal resistance dataset includes the working data and the corresponding fouling thermal resistance over a historical period. The second fouling thermal resistance threshold is used to identify the pre-set fouling thermal resistance threshold for cleaning the heat exchanger. A maintenance recommendation is generated, which indicates that the heat exchanger should be cleaned at the specified time.

2. The method according to claim 1, characterized in that, The method further includes: If the fouling thermal resistance reaches the first fouling thermal resistance threshold, or the fouling thermal resistance change rate reaches the first preset rate, a fouling trend monitoring warning is issued, wherein the first fouling thermal resistance threshold is less than the second fouling thermal resistance threshold. If the fouling thermal resistance reaches the second fouling thermal resistance threshold, or the fouling thermal resistance change rate reaches the second preset rate, a heat exchanger maintenance warning is issued, wherein the second preset rate is greater than the first preset rate. If the thermal resistance of the dirt reaches the third thermal resistance threshold, a shutdown cleaning warning will be issued, wherein the third thermal resistance threshold is greater than the second thermal resistance threshold.

3. The method according to claim 1, characterized in that, The working data includes the working data of the hot-side medium or the working data of the cold-side medium, and the reference total heat transfer coefficient includes the reference total heat transfer coefficient of the hot-side medium or the reference total heat transfer coefficient of the cold-side medium. The determination of the overall heat transfer coefficient sequence based on the working data includes: The overall heat transfer coefficient sequence of the hot-side medium is determined based on the working data of the hot-side medium, or the overall heat transfer coefficient sequence of the cold-side medium is determined based on the working data of the cold-side medium. The determination of the fouling thermal resistance sequence based on the total heat transfer coefficient sequence and the reference total heat transfer coefficient includes: A fouling thermal resistance sequence is determined based on the total heat transfer coefficient sequence of the hot-side medium and the reference total heat transfer coefficient, or a fouling thermal resistance sequence is determined based on the total heat transfer coefficient sequence of the cold-side medium and the reference total heat transfer coefficient.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: If the temperature change rate at the first moment in the working data is greater than a preset temperature change rate threshold or the flow rate change rate is greater than a preset flow rate change rate threshold, then the temperature and flow rate at the first moment are deleted to obtain the valid data in the working data. The determination of the overall heat transfer coefficient sequence based on the working data includes: Based on the valid data in the working data, the overall heat transfer coefficient sequence is determined.

5. The method according to claim 1, characterized in that, The acquisition of the heat exchanger's operating data over a period of time includes: Based on the data acquisition frequency, the temperature and flow rate of the heat exchanger are collected to obtain the operating data of the heat exchanger.

6. The method according to claim 1, characterized in that, The method further includes: The display shows the operating data, the fouling thermal resistance sequence, and the moment when the fouling thermal resistance reaches the second fouling thermal resistance threshold.

7. A system for determining the fouling state in a heat exchanger, characterized in that, The system includes: The acquisition unit is used to acquire the operating data of the heat exchanger over a period of time and the reference total heat transfer coefficient under clean conditions. The operating data is collected by sensors arranged at the inlet and outlet of the heat exchanger tube side or shell side, and the operating data includes temperature and flow rate. A determining unit is used to determine the overall heat transfer coefficient sequence based on the working data; The determining unit is further configured to determine a fouling thermal resistance sequence based on the total heat transfer coefficient sequence and the reference total heat transfer coefficient. The prediction unit is used to predict the time when the fouling thermal resistance reaches the second fouling thermal resistance threshold based on the fouling thermal resistance sequence and the pre-built prediction model. The prediction model is a time series prediction model trained based on a historical fouling thermal resistance dataset. The historical fouling thermal resistance dataset includes the working data and the corresponding fouling thermal resistance over a historical period. The second fouling thermal resistance threshold is used to identify the pre-set fouling thermal resistance threshold for cleaning the heat exchanger. A generation unit is used to generate a maintenance recommendation, which indicates that the heat exchanger should be cleaned at the specified time.

8. A computer device, characterized in that, The computer device includes a processor and memory: The memory is used to store computer programs; The processor is configured to perform the method according to any one of claims 1-6 according to the computer program.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program that, when executed by a computer device, performs the method described in any one of claims 1-6.

10. A computer program product comprising a computer program, characterized in that, When it is run on a computer device, it causes the computer device to perform the method described in any one of claims 1-6.

Images