Scale cleaning method and device, medium and electronic equipment

Abstract

The invention relates to an incrustation cleaning method and device, a medium and electronic equipment, and the method comprises the steps that first data of water flow in a preset area is collected, and the first data comprises data used for representing the water quality and the flow field state of the preset area; extracting a comprehensive feature vector of the preset area from the first data, and predicting a scaling risk level of the preset area according to the comprehensive feature vector; and according to the scaling risk grade and the comprehensive feature vector, water scale cleaning is conducted on the preset area, so that the water scale cleaning efficiency is improved.

Description

Technical Field

[0001] This disclosure relates to the field of scale prevention and control technology, specifically to a scale cleaning method, apparatus, medium, and electronic equipment. Background Technology

[0002] Wastewater spray evaporators are core equipment in industrial applications for treating high-salinity wastewater and achieving wastewater reduction. They atomize wastewater and spray it into an evaporation space at high temperatures, causing the water to evaporate and be discharged, thus concentrating the wastewater. During operation, pre-designed areas such as nozzles, pipe bends, and thin liquid film zones become high-risk areas for scaling due to intense flow field disturbances and the tendency for solutes to accumulate. Scaling can clog nozzles, reduce heat transfer efficiency, and even cause equipment shutdown, severely impacting the continuous operation of the evaporator and the achievement of wastewater discharge standards or zero-discharge targets. Therefore, controlling scaling in these pre-designated areas is crucial for ensuring the stable and efficient operation of the equipment.

[0003] Existing technologies typically rely on overall water quality indicators (such as total hardness and total salinity) to assess scaling risk. They cannot reflect the flow field disturbances and solute enrichment in localized areas such as nozzles, pipe bends, and thin liquid film areas. This results in high-risk micro-areas not being accurately identified, making it difficult to take timely and targeted intervention measures. Consequently, control measures are delayed, equipment maintenance costs increase, and even the wastewater treatment efficiency and emission reduction effect of evaporators are affected. Summary of the Invention

[0004] The purpose of this disclosure is to provide a method, apparatus, medium, and electronic device for cleaning scale, so as to improve the efficiency of scale cleaning.

[0005] To achieve the above objectives, this disclosure provides a method for removing limescale, the method comprising: Collect first data on water flow within a preset area, the first data including data characterizing the water quality and flow field state of the preset area; The comprehensive feature vector of the preset area is extracted from the first data, and the scaling risk level of the preset area is predicted based on the comprehensive feature vector. Based on the scaling risk level and the comprehensive feature vector, scale is cleaned from the preset area.

[0006] Optionally, there are multiple preset areas, and the step of cleaning scale from the preset areas based on the scaling risk level and the comprehensive feature vector includes: Based on the scaling risk level, a target area is determined from a plurality of preset areas, wherein the target area is an area with a scaling risk level greater than the preset level; Based on the scaling risk level and comprehensive feature vector corresponding to the target area, scale removal is performed on the target area.

[0007] Optionally, the step of cleaning scale from the target area based on the scaling risk level and comprehensive feature vector corresponding to the target area includes: Based on the scaling risk level of the target area, a target scaling strategy is determined from a variety of preset scaling strategies; Based on the comprehensive feature vector of the target area, the operating parameters of the target descaling strategy are determined; Based on the operating parameters, the target area is cleaned of scale using the target descaling strategy.

[0008] Optionally, the preset descaling strategy includes at least one of the following: dry vibration strategy, microbubble strategy, and scale inhibitor dosing strategy.

[0009] Optionally, predicting the scaling risk level of the preset area based on the comprehensive feature vector includes: Based on the comprehensive feature vector, the current scale parameters are calculated, and the scale parameters are used to characterize the formation trend of scale. Based on the preset correspondence between scale parameters and scale risk levels, the scale risk level corresponding to the current scale parameters is determined.

[0010] Optionally, there are multiple preset regions, and the step of extracting the comprehensive feature vector of the preset regions from the first data includes: Temporal features and spatial features are extracted from the first data respectively. The temporal features are used to characterize the changing trend of the first data, and the spatial features are used to characterize the data differences and distribution characteristics between the first data in each of the preset regions. The extracted temporal features and spatial features are weighted and fused to obtain the comprehensive feature vector.

[0011] Optionally, the step of weightedly fusing the extracted temporal features and spatial features to obtain the comprehensive feature vector includes: A first weight corresponding to the temporal feature and a second weight corresponding to the spatial feature are determined, wherein the first weight and the second weight are determined based on the historical flow field data and historical scaling risk level of the preset area; The temporal features and spatial features are weighted and fused according to the first weight and the second weight to obtain the comprehensive feature vector.

[0012] On the other hand, this disclosure also provides a scale removal device, the device comprising: The acquisition module is configured to acquire first data of water flow within a preset area, the first data including data characterizing the water quality and flow field state of the preset area; The prediction module is configured to extract a comprehensive feature vector of the preset area from the first data, and predict the scaling risk level of the preset area based on the comprehensive feature vector. The cleaning module is configured to clean scale from the preset area based on the scale risk level and the comprehensive feature vector.

[0013] On the other hand, this disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the scale removal method provided in this disclosure.

[0014] On the other hand, this disclosure also provides an electronic device, including: A memory on which computer programs are stored; A processor is configured to execute the computer program in the memory to implement the scale removal method provided in this disclosure.

[0015] By collecting first data including water quality and flow field status, the above technical solution breaks through the limitations of relying solely on overall water quality indicators and accurately captures relevant parameters for scale formation in a preset area. Secondly, it predicts the scale risk level based on the comprehensive feature vector extracted from the first data and customizes a cleaning plan based on the risk level and the comprehensive feature vector, thereby improving the accuracy of scale risk prediction and avoiding the omission of local high-risk structural areas. For example, this method can be applied to wastewater spray evaporators to extend the equipment's operating cycle and ensure the continuous and stable operation of the wastewater spray evaporator.

[0016] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating a method for cleaning limescale according to an exemplary embodiment.

[0018] Figure 2 This is a structural block diagram of a scale removal system according to an exemplary embodiment.

[0019] Figure 3 This is a block diagram illustrating a scale removal device according to an exemplary embodiment.

[0020] Figure 4 A block diagram of an electronic device is shown according to an exemplary embodiment.

[0021] Figure 5A block diagram of an electronic device is shown according to an exemplary embodiment. Detailed Implementation

[0022] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0023] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in accordance with the relevant data protection laws and policies of the country where the location is situated, and with the authorization granted by the owner of the relevant device.

[0024] In the following description, the words "first" and "second" are used only to distinguish the purpose of the description and should not be interpreted as indicating or implying relative importance or order.

[0025] It is worth noting that the scale removal method provided in this disclosure can be applied to a scale removal system that can remove scale from wastewater spray evaporators.

[0026] Figure 1 This is a flowchart illustrating a method for removing limescale according to an exemplary embodiment. Please refer to... Figure 1 The limescale removal method may include the following steps: In step S11, the first data of water flow within the preset area is collected.

[0027] In one embodiment, the preset areas are multiple locations pre-defined in the wastewater spray evaporator based on historical scaling locations and experience, such as the spray nozzles, pipe bends, and thin liquid film areas of the wastewater spray evaporator.

[0028] The first data includes data used to characterize the water quality and flow field state of the preset area.

[0029] In step S12, a comprehensive feature vector of the preset area is extracted from the first data, and the scaling risk level of the preset area is predicted based on the comprehensive feature vector.

[0030] In step S13, scale is cleaned from the preset area according to the scale risk level and the comprehensive feature vector.

[0031] In one embodiment, the scale removal system has water quality sensors and flow field sensors arranged in an array at the nozzles, pipe bends, and thin liquid film areas to form a multi-point monitoring network covering key areas, thereby collecting the first data. Each sensor uploads the collected signal to the control unit of the scale removal system in real time through a data acquisition interface. The control unit manages and schedules the raw signals in a unified manner.

[0032] The first data includes water quality data collected by a water quality sensor and flow field data collected by a flow field sensor. The water quality data includes at least one of the water temperature, pH value, conductivity and hardness of the water flow within the preset area. The flow field data includes at least one of the flow velocity, vortex conditions and liquid film thickness distribution of the water flow within the preset area.

[0033] In another embodiment, the scale removal system can achieve refined acquisition of local water quality and flow field characteristics by preprocessing the collected first data. Specifically, the collected water quality data and flow field data are denoised and filtered to eliminate high-frequency interference signals, and the filtered water quality data and flow field data are standardized to form first data in a unified format.

[0034] For example, the control unit of the scale removal system performs noise reduction processing on the collected first data (water quality data and flow field data) to remove sensor noise, environmental interference signals, and abnormal data points. It also filters the first data to eliminate high-frequency interference components, for example, using low-pass filtering or weighted moving average filtering. During the filtering process, the following formula 1 can be used for weighted moving average processing: Formula 1:

[0035] in, This represents the filtered signal. This represents the original acquired signal, and N is the selected sampling window length.

[0036] The filtered first data is further standardized to normalize the physical quantities (first data) measured by each sensor into a data vector of a uniform format. For example, the following formula 2 can be used to map the values ​​to the range of 0 to 1: Formula 2:

[0037] Where X represents the original acquired data after filtering or the first data after denoising processing. Corresponding to the historical minimum value of the first data point, and This corresponds to the historical maximum value of the first data point, forming standardized feature data.

[0038] The standardized first data is transmitted to the feature analysis unit of the scale removal system via a data interface. The control unit organizes the data according to spatial location and time sequence based on the preset area division and sensor layout logic, so as to analyze the local parameter change trend and flow field distribution of the target area in the subsequent process. During the data transmission, wired or wireless communication methods, such as Ethernet, industrial bus or low power wireless communication, can be used to achieve data synchronization and real-time updates. The first data record keeps both timestamp and spatial identifier to ensure that the location and collection time of the target area can be accurately matched in the subsequent feature extraction and risk assessment process.

[0039] The standardized first data generated through the above steps is used to provide data for subsequent scale removal steps, thus achieving complete data support and logical closed loop for scale prevention and control.

[0040] In one embodiment, the scale removal system is pre-set with multiple scale risk levels, such as low, medium, high, or level 1, level 2, ..., n, etc. Each scale risk level corresponds to a comprehensive feature vector range, thereby predicting the scale risk level of each preset area based on the comprehensive feature vector.

[0041] Finally, based on the scaling risk level and comprehensive feature vector of each preset area, a descaling strategy is determined for each preset area to achieve scale removal.

[0042] By collecting first data including water quality and flow field status, the above technical solution breaks through the limitations of relying solely on overall water quality indicators and accurately captures relevant parameters for scale formation in a preset area. Secondly, it predicts the scale risk level based on the comprehensive feature vector extracted from the first data and customizes a cleaning plan based on the risk level and the comprehensive feature vector, thereby improving the accuracy of scale risk prediction and avoiding the omission of local high-risk structural areas. For example, this method can be applied to wastewater spray evaporators to extend the equipment's operating cycle and ensure the continuous and stable operation of the wastewater spray evaporator.

[0043] Optionally, there are multiple preset areas, and the above step S13 can be performed to remove limescale in the following ways: The first step is to determine a target area from among the multiple preset areas based on the scaling risk level, wherein the target area is an area where the scaling risk level is greater than the preset risk level.

[0044] It is worth noting that the target area can be understood as an area with a high risk of scaling.

[0045] The second step is to clean the scale in the target area based on the scale risk level and comprehensive feature vector corresponding to the target area.

[0046] The above method targets scale removal in multiple pre-defined areas. Through a step-by-step logic of risk priority screening and customized intervention, it achieves efficient resource allocation and improved cleaning accuracy. The first step selects target areas based on scale risk levels (only high-risk areas exceeding pre-defined values ​​are included). This prioritizes high-risk areas such as nozzles and pipe bends, avoiding indiscriminate treatment of low-risk areas (such as gentle pipe sections), reducing ineffective consumption of energy from micro-vibration devices and scale inhibitors, and significantly improving the efficiency of intervention resource utilization. The second step customizes cleaning solutions based on the risk level and comprehensive feature vector of the target areas. For example, nozzles (comprehensive features: high vortex intensity, high hardness) and pipe bends (comprehensive features: high liquid film thickness, high conductivity), both high-risk areas, can be matched with differentiated solutions using different descaling strategies, avoiding the problem of insufficient adaptability of a single solution. Overall, this achieves targeted and adaptable scale removal across multiple areas, ensuring scale-free operation in critical areas of the evaporator, reducing equipment maintenance costs, and improving the continuous operational stability of the scale removal system.

[0047] In one implementation, the second step described above can be performed through the following methods: First, based on the scaling risk level of the target area, a target scaling strategy is determined from a variety of preset scaling strategies.

[0048] Then, based on the comprehensive feature vector of the target area, the operating parameters of the target descaling strategy are determined.

[0049] Finally, based on the operating parameters, the target area is cleaned of scale using the target descaling strategy.

[0050] In the specific implementation process, the scaling risk level information of each preset area is first determined, and the preset areas with different scaling risk levels are marked as high risk, medium risk or low risk, so as to provide a basis for subsequent descaling strategies. The scale cleaning system determines the required operating parameters for each target area based on the comprehensive feature vector of the preset area, combined with water quality parameters, flow field distribution and historical scaling data.

[0051] In one embodiment, the preset descaling strategy includes at least one of a dry vibration strategy, a microbubble strategy, and a scale inhibitor dosing strategy.

[0052] The scale removal system can determine the frequency and amplitude of dry vibration operation required for each target area based on the comprehensive feature vector, combined with water quality parameters, flow field distribution and historical scale data, as well as the bubble diameter, spraying time and spraying position of the microbubble strategy. At the same time, it can determine the priority order and quantitative parameters of the scale inhibitor addition based on the comprehensive feature vector of the target area and the scale inhibitor addition strategy.

[0053] In one embodiment, a dry vibration actuator is activated for each target area to perform vibration operation according to the frequency and amplitude determined in the descaling strategy corresponding to the target area.

[0054] Example 1: The operating parameters of the dry vibration strategy can be obtained through the following calculations 3 and 4: Formula 3:

[0055] in, The vibration frequency, For adjustment coefficients, This is the vibration demand function based on the comprehensive feature vector F.

[0056] Formula 4:

[0057] in, For amplitude, This is the amplitude adjustment coefficient. This is the vibration amplitude demand function.

[0058] In another embodiment, a microbubble generator is activated for each target area, and microbubble operation is performed according to the bubble diameter, spray time, and spray position determined in the descaling strategy corresponding to the target area.

[0059] Example 2: In the operating parameters of the microbubble strategy, the bubble diameter... and injection time This can be expressed as the following calculation formulas 5 and 6 respectively: Formula 5:

[0060] Formula 6:

[0061] in, and This is an adjustable coefficient. and These represent the bubble diameter requirement function and the injection time requirement function based on the comprehensive feature vector, respectively, to ensure that dry vibration and microbubble operation are accurately matched with the comprehensive feature vector.

[0062] In yet another embodiment, the operating parameters of the scale inhibitor dosing strategy include the coordinates of the scale inhibitor dosing location for each target area and the dosing amount. and the time of application The scale inhibitor dosing device is controlled to perform targeted micro-dosing in the target area according to the operating parameters.

[0063] Example 3: The dosage can be determined based on the comprehensive characteristic vector F and the scaling risk level R using the following formula 7: Formula 7:

[0064] in, For adjustment coefficients, This represents the anti-scaling requirement function.

[0065] Addition time It can be determined by the following formula 8: Formula 8:

[0066] in, For time coefficient, Let be the scale inhibitor response function.

[0067] Based on the analyzed dosing parameters, the control unit drives the scale inhibitor dosing device to perform targeted micro-dosing at designated locations in each target area. The dosing device can be an adjustable flow valve, a micro-injection pump, or similar equipment. By precisely controlling the valve opening, pump speed, or nozzle angle, it ensures that the scale inhibitor is evenly distributed in the target area and strictly follows the dosing amount and dosing time specified in the strategy. At the same time, it is synchronized and coordinated with the dry vibration strategy and the microbubble strategy to enhance the effectiveness and accuracy of the scale inhibitor's action.

[0068] The following explanation uses an optional embodiment. First, a sensor array is arranged at the nozzle to collect water quality data (water temperature, pH value, hardness) and flow field data (local flow velocity, eddy conditions) over 3 hours. Temporal characteristics are extracted: water temperature rises from 50℃ to 55℃, with a change trend of 0.0028℃ / s; pH peak value is 7.8, with a fluctuation rate of 3%; hardness peak value is 300mg / L, with a fluctuation rate of 8%.

[0069] Then, spatial features are extracted: the conductivity difference between the nozzle area and the adjacent pipe bend area is 0.2 S / m, and the local flow field vortex intensity is 0.9 m / s² (higher than the average of 0.3 m / s² in the surrounding area). Due to the strong dynamics of the nozzle flow field, the temporal feature weight is 0.6 and the spatial feature weight is 0.4, forming a comprehensive feature vector [0.0028, 7.8, 3%, 300, 8%, 0.2, 0.9].

[0070] Finally, the scale formation trend value (scale parameter) was calculated to be 0.85 (preset risk level is 0.7), indicating a high scale risk level for this preset area. This preset area was then designated as the target area, i.e., an area with a high scale risk. Because the target area has a high scale risk level, and the comprehensive feature vector indicates strong vortex and high water hardness in this area, the descaling strategy was determined to be a combination of dry vibration, microbubble, and scale inhibitor application. Further, the operating parameters for the dry vibration strategy were determined to be: frequency 25kHz (matching vortex frequency), amplitude 6μm (adjusted according to peak hardness); the operating parameters for the microbubble strategy were: bubble diameter 40μm (adapting to nozzle size), spray time 15s (covering the peak period of crystal nucleation), and spray position directly opposite the nozzle outlet; the operating parameters for the scale inhibitor application strategy were: dosage 0.6mL (calculated based on peak hardness), application time synchronized with micro-vibration, and application position close to the inner wall of the nozzle.

[0071] Then, the cleaning operation is performed. The dry vibration device is started and vibrates the inner wall of the nozzle according to the parameters. The microbubble generator sprays microbubbles into the flow field of the nozzle to disturb the solute distribution. The scale inhibitor dosing device accurately injects scale inhibitor, which works in conjunction with the vibration and bubble operation.

[0072] During the descaling process, monitor the first data from the spray nozzle. If the hardness is still higher than 280 mg / L, adjust the micro-vibration amplitude to 7 μm and add 0.2 mL of scale inhibitor.

[0073] In addition, the scale inhibitor dosing module of the scale removal system is equipped with a real-time monitoring and recording unit. It collects parameters, device status and environmental information in real time for each dosing process. The recorded data includes dosing flow rate, time, location and local water quality status, and feeds the data back to the control unit. The control unit compares the actual dosing status with the strategy parameters. If a deviation is found, it automatically adjusts the dosing device parameters to make the actual dosing amount consistent with the strategy requirements, thus forming a closed-loop control process. This enables precise management of the targeted micro-dosing of scale inhibitor in the target area, providing data support and operational basis for overall intelligent anti-scaling control.

[0074] It is worth noting that the scale inhibitor dosing strategy prioritizes dosing in areas with high crystal nucleus (scale) formation rates and high scale risk levels, based on the scale parameters (characterizing scale formation trends) and operating load of the preset area. At the same time, it determines the dosing amount, dosing time, and specific location, forming a structured output to guide the micro-area intervention unit and the scale inhibitor dosing module to coordinate the intervention operation.

[0075] The descaling strategy corresponding to the target area is output to the control unit in the form of data structure or control command. The scale cleaning system monitors the status of the preset area and execution feedback in real time. The strategy parameters are optimized through a closed-loop adjustment mechanism to ensure that the dry vibration strategy, microbubble strategy and scale inhibitor dosing strategy are coordinated to achieve precise intervention in the target area. At the same time, the weighting coefficient can be dynamically adjusted according to the changes in the comprehensive feature vector of the preset area based on historical operating data, so that the descaling strategy can continuously adapt to water quality fluctuations and flow field changes, forming a complete operating logic to support the intelligent execution of scale prevention control of wastewater spray evaporator.

[0076] During operation, the dry vibration and microbubble operation parameters and status information in the preset area are recorded in real time. The scale removal system can update the weighted parameters of dry vibration and microbubble operation based on historical operation data and dynamic changes in comprehensive feature vectors. Through closed-loop control algorithm, the execution effect is continuously optimized to ensure that dry vibration operation and microbubble operation in the preset area are carried out in synergy, so as to achieve precise intervention in the target area. At the same time, it provides data support for subsequent targeted micro-dosing of scale inhibitor and overall anti-scaling control strategy.

[0077] In an optional implementation, step S12 above can predict the scaling risk level of a preset area in the following way: Calculate the current scale parameters based on the comprehensive feature vector.

[0078] The scale parameters are used to characterize the formation trend of scale.

[0079] Based on the preset correspondence between scale parameters and scale risk levels, the scale risk level corresponding to the current scale parameters is determined.

[0080] In one embodiment, the comprehensive feature vector is input into the risk assessment unit of the scale removal system. The scale removal system performs temporal and spatial feature fusion analysis on the comprehensive feature vector and calculates scale parameters, i.e., the crystal nucleus (scale) formation trend, based on the comprehensive feature vector. The scale parameters can be represented by the model calculation function (calculation formula 9): Formula 9:

[0081] in, denoted as the scale parameter for the preset area, and f as a prediction function based on the comprehensive feature vector. This prediction function can be calculated using statistical models, machine learning models, or rule-based methods to quantify the scale potential of the preset area.

[0082] Scale parameters are further mapped to the scaling risk level using the following formula 10: Formula 10:

[0083] Where R is the scaling risk level, which can be divided into low, medium and high levels. g is a mapping function based on the preset correspondence between scale parameters and scaling risk level. This mapping function can be determined according to the scale formation rate threshold and historical scaling data, so that the risk level can be used for the generation and optimization of subsequent dry vibration operation, microbubble operation and scale inhibitor dosing strategy, realizing a complete logical closed loop of anti-scaling control.

[0084] In an optional implementation, there are multiple preset regions, and step S12 above can extract the comprehensive feature vector of the preset regions from the first data in the following way: First, temporal features and spatial features are extracted from the first data, respectively.

[0085] The temporal features are used to characterize the changing trend of the first data, and the spatial features are used to characterize the data differences and distribution characteristics among the first data in each of the preset regions.

[0086] For example, time-series features include the local parameter variation trends, peak values, standard deviations, and volatility of the first data within the preset region, such as the local parameter variation trends. It can be expressed by the following formula 11: Formula 11:

[0087] in, This is the first data point at the current sampling time. This is the first data point from the previous sampling time. For time intervals, the peak value of the local parameter change trend represents the local maximum value in the time series.

[0088] For example, volatility can be represented by the following formula 12 to ensure that dynamic behavioral characteristics are fully captured.

[0089] Formula 12:

[0090] in, Here, P represents the sampled value, N represents the mean, and N represents the number of sampled points.

[0091] In another example, spatial features include parameter differences of the first data within each preset region and local flow field distribution characteristics, to reflect water quality differences and uneven flow field distribution between different preset regions.

[0092] For example, spatial feature extraction involves comparing first data from adjacent preset regions. and Difference To achieve this.

[0093] in It can be the Euclidean norm or other suitable distance measure to quantify the differences between preset regions. The flow field distribution characteristics are generated by statistical analysis of the local velocity vector field, vortex intensity and liquid film thickness distribution in the preset region to generate feature vectors.

[0094] Second, the extracted temporal features and spatial features are weighted and fused to obtain the comprehensive feature vector.

[0095] In one implementation, the extracted temporal and spatial features can be weighted and fused to obtain the comprehensive feature vector using the following method: First, determine the first weight corresponding to the temporal feature and the second weight corresponding to the spatial feature.

[0096] The first and second weights are determined based on the historical flow field data and historical scaling risk levels of the preset area. It is worth noting that the historical flow field data includes past local flow velocity changes, vortex occurrence frequency, and liquid film thickness fluctuations in the area. The stronger the flow field dynamics (such as frequent vortices), the greater the impact of temporal characteristics on scaling, and the higher the first weight. The historical scaling risk level is the past scaling risk record of the area. If scaling is frequent in the past due to differences in micro-interval parameters (spatial characteristics), the second weight will be increased accordingly. The sum of the first and second weights is actually 1, ensuring the numerical stability of the fused feature vector.

[0097] Then, based on the first weight and the second weight, the temporal features and the spatial features are weighted and fused to obtain the comprehensive feature vector.

[0098] In one embodiment, temporal and spatial features are weighted and fused according to the dynamic characteristics of the flow field in a preset region and the trend of historical data, for example, by the following calculation formula 13: Formula 13:

[0099] Where F is the comprehensive feature vector, F s For spatial characteristics, F t For time-series characteristics, w s w represents the second weight corresponding to the spatial features. t The second weight corresponds to the temporal characteristics, and the weights are the spatial characteristics and temporal characteristics, respectively. The first weight and the second weight are automatically adjusted based on the dynamics of the historical flow field and the historical crystal nucleus formation trend of the preset region to ensure that the comprehensive feature vector can fully reflect the scaling risk of the preset region.

[0100] In one embodiment, this disclosure also provides a scale removal system, see [link to relevant documentation]. Figure 2As shown, the scale removal system includes a data detection unit, a risk prediction unit, a strategy generation unit, a scale removal execution unit, a scale inhibitor addition unit, and an adaptive optimization unit.

[0101] The micro-area monitoring unit is used to collect initial data and perform preprocessing in nozzles, pipe bends, and thin liquid film areas.

[0102] The risk prediction unit is used to extract features based on the first data, analyze the scale formation trend, and generate a scale risk level.

[0103] The strategy generation unit is used to determine the target area based on the scaling risk level and generate descaling strategies and intervention parameters.

[0104] The descaling execution unit is used to perform micro-vibration and micro-bubble operations within the target area, and adjusts the operating parameters corresponding to the descaling strategy according to the intervention parameters.

[0105] The scale inhibitor dosing unit is used to perform targeted micro-dosing of scale inhibitor within the target area. The scale inhibitor dosing unit works in coordination with the descaling execution unit.

[0106] The adaptive optimization unit is used to compare the scale risk level with the actual scale state based on the collected water quality data, flow field data and the current scale removal strategy, and optimize the current scale removal strategy based on the difference.

[0107] For example, optimizing the current cleaning strategy includes the following steps: Step 1: Receive monitoring data from each preset area, operating parameters of the dry vibration strategy, operating parameters of the microbubble strategy, and operating parameters and execution status records of the scale inhibitor dosing strategy.

[0108] Step 2: Compare the scaling risk level information of each preset area with the actual operating status to identify strategy deviations.

[0109] Step 3: For each target area, adjust the operating parameters of the dry vibration strategy and the microbubble strategy to match the comprehensive feature vector and risk level of the target area.

[0110] Step 4: Adjust the scale inhibitor dosing parameters to optimize the scale inhibitor dosing strategy.

[0111] In the specific implementation process, the adaptive optimization unit first receives real-time monitoring data from each preset area, including parameters such as water temperature, pH value, conductivity, hardness, local flow velocity, vortex conditions, and liquid film thickness within the preset area. Simultaneously, it collects dry vibration operation parameters from the preset area. and ,in The vibration frequency, For vibration amplitude, microbubble operating parameters , as well as ,in The diameter of the bubble. For the spraying time, Instructions for spraying location and scale inhibitor dosing parameters , as well as ,in For dosage, For the time of addition, Record the injection location and its execution status.

[0112] The adaptive optimization unit compares the actual monitoring data with the scaling risk level to identify strategy deviations, which can be expressed by the following formula 14: Formula 14:

[0113] in, This is an indicator of the actual scaling condition. To predict the risk level, This represents the strategy deviation; the optimization process is triggered when the deviation exceeds a set threshold.

[0114] Then, based on the deviation analysis results, the module adjusts the dry vibration operation parameters for each high-risk area (i.e., the target area) to match the vibration frequency fv and amplitude Av with the comprehensive characteristic vector F and the scaling risk level R. The adjustment method can be expressed as the following calculation formulas 15 and 16: Formula 15:

[0115] Formula 16:

[0116] in and For adjustment coefficients, and This is the vibration demand function.

[0117] At the same time, adjust the operating parameters of the microbubble strategy. , as well as To match the flow field characteristics and scaling trends (determined based on scale parameters), ensure that microbubble operation covers the target area and is coordinated with dry vibration operation.

[0118] In the specific implementation process, the adaptive optimization unit further adjusts the scale inhibitor dosing parameters. , as well as The scale inhibitor dosage strategy is optimized based on the scaling risk level, descaling operation feedback, and historical data trends. The adjustment method can be expressed as the following calculation formulas 17 and 18: Formula 17:

[0119] Formula 18:

[0120] in and For coefficients, and The module generates a scale inhibitor dosing demand function. After adjustment, the parameters are sent from the control unit to the dry vibration, microbubble, and scale inhibitor dosing devices in the preset area. During the optimization process, the module continuously monitors the execution status, records the adjustment effect and feedback data in real time, so as to form a closed-loop adaptive control, realize the dynamic optimization and precise management of the descaling strategy, and ensure that the operating parameters, dosing parameters and risk levels of each high-risk area are consistent, providing reliable adaptive control capability for the overall scale cleaning system.

[0121] See Figure 3 As shown, this disclosure also provides a scale removal device 200, which includes a data acquisition module 201, a prediction module 202, and a cleaning module 203.

[0122] The acquisition module 201 is configured to acquire first data of water flow within a preset area, the first data including data characterizing the water quality and flow field state of the preset area; The prediction module 202 is configured to extract a comprehensive feature vector of the preset area from the first data, and predict the scaling risk level of the preset area based on the comprehensive feature vector. The cleaning module 203 is configured to clean the scale in the preset area based on the scale risk level and the comprehensive feature vector.

[0123] Optionally, there are multiple preset areas, and the cleaning module 203 is configured as follows: Based on the scaling risk level, a target area is determined from a plurality of preset areas, wherein the target area is an area with a scaling risk level greater than the preset level; Based on the scaling risk level and comprehensive feature vector corresponding to the target area, scale removal is performed on the target area.

[0124] Optionally, the cleaning module 203 is configured to: Based on the scaling risk level of the target area, a target scaling strategy is determined from a variety of preset scaling strategies; Based on the comprehensive feature vector of the target area, the operating parameters of the target descaling strategy are determined; Based on the operating parameters, the target area is cleaned of scale using the target descaling strategy.

[0125] Optionally, the preset descaling strategy includes at least one of the following: dry vibration strategy, microbubble strategy, and scale inhibitor dosing strategy.

[0126] Optionally, the prediction module 202 is configured to: Based on the comprehensive feature vector, the current scale parameters are calculated, and the scale parameters are used to characterize the formation trend of scale. Based on the preset correspondence between scale parameters and scale risk levels, the scale risk level corresponding to the current scale parameters is determined.

[0127] Optionally, there are multiple preset regions, and the prediction module 202 is configured as follows: Temporal features and spatial features are extracted from the first data respectively. The temporal features are used to characterize the changing trend of the first data, and the spatial features are used to characterize the data differences and distribution characteristics between the first data in each of the preset regions. The extracted temporal features and spatial features are weighted and fused to obtain the comprehensive feature vector.

[0128] Optionally, the prediction module 202 is configured to: A first weight corresponding to the temporal feature and a second weight corresponding to the spatial feature are determined, wherein the first weight and the second weight are determined based on the historical flow field data and historical scaling risk level of the preset area; The temporal features and spatial features are weighted and fused according to the first weight and the second weight to obtain the comprehensive feature vector.

[0129] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0130] Figure 4 This is a block diagram illustrating an electronic device 700 according to an exemplary embodiment. Figure 4 As shown, the electronic device 700 may include a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0131] The processor 701 controls the overall operation of the electronic device 700 to complete all or part of the steps in the aforementioned limescale cleaning method. The memory 702 stores various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 703 may include a screen and audio components. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 702 or transmitted via communication component 705. The audio component also includes at least one speaker for outputting audio signals. I / O interface 704 provides an interface between processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof; therefore, the corresponding communication component 705 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0132] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described scale removal method.

[0133] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-described scale removal method. For example, the computer-readable storage medium may be the memory 702 including program instructions, which may be executed by the processor 701 of the electronic device 700 to complete the above-described scale removal method.

[0134] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a processor, which, when executed by the processor, implements the steps of the above-described scale removal method.

[0135] Figure 5 This is a block diagram illustrating an electronic device 1900 according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. (Refer to...) Figure 5 The electronic device 1900 includes a processor 1922, which may be one or more, and a memory 1932 for storing computer programs executable by the processor 1922. The computer program stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor 1922 may be configured to execute the computer program to perform the aforementioned scale removal method.

[0136] Additionally, the electronic device 1900 may also include a power supply component 1926 and a communication component 1950. The power supply component 1926 can be configured to perform power management of the electronic device 1900, and the communication component 1950 can be configured to enable communication of the electronic device 1900, such as wired or wireless communication. Furthermore, the electronic device 1900 may also include an input / output (I / O) interface 1958. The electronic device 1900 can operate on an operating system, such as Windows Server, stored in memory 1932. TM Mac OS X TM Unix TM Linux TM etc.

[0137] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-described scale removal method. For example, the computer-readable storage medium may be the memory 1932 including program instructions, which may be executed by the processor 1922 of the electronic device 1900 to complete the above-described scale removal method.

[0138] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a processor, which, when executed by the processor, implements the steps of the above-described scale removal method.

[0139] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0140] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0141] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A scale cleaning method characterized by, The method comprises: collecting first data of water flow in a preset region, the first data comprising data for representing water quality and flow field state of the preset region; extracting a comprehensive feature vector of the preset region from the first data, and predicting a fouling risk level of the preset region according to the comprehensive feature vector; cleaning scale in the preset region according to the fouling risk level and the comprehensive feature vector.

2. The scale cleaning method according to claim 1, characterized by, The preset region is multiple, and the cleaning scale in the preset region according to the fouling risk level and the comprehensive feature vector comprises: determining a target region from the multiple preset regions according to the fouling risk level, the target region being a region with a fouling risk level greater than a preset risk level; cleaning scale in the target region according to the fouling risk level and the comprehensive feature vector corresponding to the target region.

3. The scale cleaning method according to claim 2, characterized by, The cleaning scale in the target region according to the fouling risk level and the comprehensive feature vector corresponding to the target region comprises: determining a target descaling strategy from multiple preset descaling strategies according to the fouling risk level of the target region; determining an operation parameter of the target descaling strategy according to the comprehensive feature vector of the target region; cleaning scale in the target region by the target descaling strategy according to the operation parameter.

4. The scale cleaning method according to claim 3, characterized by, The preset descaling strategy comprises at least one of a dry vibration strategy, a microbubble strategy, and a scale inhibitor injection strategy.

5. The scale cleaning method according to claim 1, characterized by, The prediction of the fouling risk level of the preset region according to the comprehensive feature vector comprises: calculating a current scale parameter according to the comprehensive feature vector, the scale parameter being used to represent a formation trend of scale; determining a fouling risk level corresponding to the current scale parameter according to a preset corresponding relationship between scale parameters and fouling risk levels.

6. The scale cleaning method according to claim 1, characterized by, The extraction of the comprehensive feature vector of the preset region from the first data comprises: extracting time sequence features and spatial features from the first data respectively, the time sequence features being used to represent a change trend of the first data, and the spatial features being used to represent data difference and distribution characteristics among the first data of each preset region; weighting and fusing the extracted time sequence features and spatial features to obtain the comprehensive feature vector.

7. The scale cleaning method according to claim 6, characterized by, The weighting and fusing of the extracted time sequence features and spatial features to obtain the comprehensive feature vector comprises: determining a first weight corresponding to the time sequence features and a second weight corresponding to the spatial features, the first weight and the second weight being determined according to historical flow field data and historical fouling risk levels of the preset region; weighting and fusing the time sequence features and the spatial features according to the first weight and the second weight to obtain the comprehensive feature vector.

8. A scale cleaning device characterized by, The device comprises: a collection module configured to collect first data of water flow in a preset region, the first data comprising data for representing water quality and flow field state of the preset region; The prediction module is configured to extract a comprehensive feature vector of the preset area from the first data, and predict a fouling risk level of the preset area according to the comprehensive feature vector. The cleaning module is configured to clean scale of the preset area according to the fouling risk level and the comprehensive feature vector.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the scale cleaning method in any one of claims 1-7.

10. An electronic device, comprising: The program is executed by the processor to implement the scale cleaning method in any one of claims 1-7. The program is executed by the processor to implement the scale cleaning method in any one of claims 1-7. The program is executed by the processor to implement the scale cleaning method in any one of claims 1-7. The program is executed by the processor to implement the scale cleaning method in any one of claims 1-7.

Images