A control method and device for a sludge removal vehicle of a horizontal-flow sedimentation tank and a storage medium

Abstract

The application discloses a kind of horizontal flow sedimentation tank sludge car control method, equipment and storage medium, it is related to water treatment technical field.Control method, first by silt accumulation prediction model obtains predicted accumulation distribution area, recommended sludge discharge interval period and predicted speed benchmark value;When meeting recommended sludge discharge interval period, sludge discharge line is started;In sludge discharge process, according to the sludge concentration of sludge discharge pipe mouth belongs to concentration fuzzy set, adjust sludge discharge line speed;When sludge concentration belongs to adjacent two concentration fuzzy sets simultaneously, using membership function is combined with corresponding predicted speed benchmark value and is solved fuzzy and obtains sludge discharge line speed.The sludge car control method of the application embodiment generates sludge discharge strategy dynamically by silt accumulation prediction model, and realizes the self-adaptive adjustment of sludge discharge line speed by combining sludge concentration fuzzy control, can dynamically adjust sludge discharge line speed according to real-time silt distribution and sludge concentration, avoid high silt accumulation area sludge discharge effect not good and low silt accumulation area energy waste.

Description

Technical Field

[0001] This application relates to the field of water treatment technology, and in particular to a method, equipment and storage medium for controlling sludge discharge vehicles in horizontal flow sedimentation tanks. Background Technology

[0002] During operation, wastewater flows at a uniform speed along the length of the sedimentation tank in a water plant. Due to gravity settling, the sludge exhibits a distinct gradient distribution: in the initial influent section, the flow velocity slows down, and a large amount of suspended solids settle, resulting in a large amount of sludge at the bottom and a high sludge concentration. As the water continues to flow towards the later sections, most of the sludge has settled, leaving the water relatively clear with less sludge at the bottom and virtually no deposited sludge. However, the actual sludge deposition does not strictly follow a linear downward trend; non-linear changes often occur along the sludge truck's path, such as an increase in sludge in some areas followed by a gradual decrease. Traditional sludge truck control modes only use three relatively fixed speed settings (high, medium, and low), which cannot adapt to the dynamic changes in sludge distribution. When the sludge truck operates at a fixed speed, in high-sludge areas, the speed may be too fast, leading to incomplete sludge removal and residual sludge affecting subsequent treatment; in low-sludge areas, the speed may be too slow, resulting in energy waste and reduced operating efficiency. This static control strategy is difficult to match with the real-time sludge condition in the sedimentation tank, resulting in unstable sludge removal effect and easy problems of insufficient or excessive sludge removal, which in turn affects the overall operating efficiency of the sedimentation tank and the stability of the effluent water quality. Summary of the Invention

[0003] Based on this, the purpose of this application is to provide a method, equipment and storage medium for controlling sludge discharge vehicles in horizontal sedimentation tanks, so as to improve sludge discharge efficiency.

[0004] To achieve the above objectives, in a first aspect, embodiments of this application provide a method for controlling a sludge discharge vehicle in a horizontal flow sedimentation tank, which includes the following steps: Input real-time operational data into the siltation prediction model to obtain the predicted siltation distribution area, recommended sludge discharge interval, and predicted velocity benchmark value. The predicted siltation distribution area is divided into high siltation area, medium siltation area, and low siltation area. The predicted velocity benchmark value is divided into low velocity benchmark corresponding to high siltation area, medium velocity benchmark corresponding to medium siltation area, and high velocity benchmark corresponding to low siltation area. Start the sludge discharge vehicle when the recommended sludge discharge interval is met; The sludge discharge vehicle speed is adjusted according to the concentration fuzzy set to which the sludge concentration at the sludge discharge pipe outlet belongs. When the sludge concentration belongs to two adjacent concentration fuzzy sets, the sludge discharge vehicle speed is obtained by defuzzifying the fuzzy set using the membership function and the corresponding predicted speed benchmark value. When the sludge concentration belongs to only one concentration fuzzy set, the sludge discharge vehicle speed is the predicted speed benchmark value corresponding to that concentration fuzzy set.

[0005] In one embodiment, the real-time operational data input to the sludge accumulation prediction model includes: total influent volume for each stage, influent turbidity, effluent turbidity, and shutdown interval duration.

[0006] In one embodiment, the concentration fuzzy set is divided into a low-concentration subset, a medium-concentration subset, and a high-concentration subset. The low-concentration subset overlaps with the medium-concentration subset, and the high-concentration subset overlaps with the medium-concentration subset. The high-concentration subset corresponds to the low-speed reference, the medium-concentration subset corresponds to the medium-speed reference, and the low-concentration subset corresponds to the high-speed reference.

[0007] In one embodiment, when the sludge concentration belongs to two adjacent fuzzy concentration sets simultaneously, the sludge discharge vehicle speed is obtained by defuzzifying the fuzzy set using a membership function combined with the corresponding predicted velocity benchmark value, including: When the sludge concentration belongs to two adjacent fuzzy concentration sets at the same time, the membership degree of the sludge concentration to each fuzzy concentration set is calculated using the triangular membership function, and then the sludge discharge vehicle speed is calculated using the maximum membership average method.

[0008] In one embodiment, a triangular membership function is used to calculate the membership degree of the sludge concentration to each concentration fuzzy set: When a≤x≤m, then μ(x)=(xa) / (ma), When m ≤ x ≤ b, then μ(x) = (bx) / (bm). When x b, then μ(x) = 0; Where μ(x) is the membership degree, x is the sludge concentration at the sludge discharge pipe inlet, a is the minimum value of the concentration fuzzy set, m is the median value of the concentration fuzzy set, and b is the maximum value of the concentration fuzzy set.

[0009] In one embodiment, in the low concentration subset, a=0, m=0.07, b=0.14; in the medium concentration subset, a=0.1, m=0.2, b=0.3; and in the high concentration subset, a=0.25, m=0.625, b=1.

[0010] In one embodiment, the sludge discharge vehicle speed is calculated using the maximum membership degree average method: Uout=(μ L (x)*f L +μ M (x)*f M +μ H (x)*f H ) / (μ L (x)+μ M (x)+μ H (x)) Where Uout is the output sludge discharge vehicle speed, μ L (x) represents the membership degree of the low-concentration subset, μM (x) represents the membership degree of the medium-concentration subset, μ H (x) represents the membership degree of the high-concentration subset, f L For the high-speed benchmark corresponding to the low-concentration subset, f M f is the medium-velocity baseline corresponding to the medium-concentration subset. H This is the low-speed benchmark corresponding to the high-concentration subset.

[0011] In one embodiment, the sludge discharge vehicle control method for a horizontal flow sedimentation tank further includes: training a sludge accumulation prediction model based on historical sludge discharge operating data, wherein the historical sludge discharge operating data includes: total influent volume during intervals, influent turbidity during intervals, effluent turbidity during intervals, stopping interval duration, high-speed benchmark for vehicle operation, sludge concentration during high-speed operation, duration of high-speed operation, medium-speed benchmark for vehicle operation, sludge concentration during medium-speed operation, duration of medium-speed operation, low-speed benchmark for vehicle operation, sludge concentration during low-speed operation, and duration of low-speed operation.

[0012] The sludge discharge vehicle control method of the present application embodiment dynamically generates a sludge discharge strategy through a sludge accumulation prediction model, and combines fuzzy control of sludge concentration to achieve adaptive adjustment of the sludge discharge vehicle speed. It can dynamically adjust the sludge discharge vehicle speed according to the real-time sludge distribution and sludge concentration, avoid poor sludge discharge effect in high sludge accumulation areas and energy waste in low sludge accumulation areas, improve sludge discharge efficiency and effect, and help improve the operational stability of sedimentation tanks.

[0013] Secondly, this application also provides a computer device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned method for controlling the sludge discharge vehicle in a horizontal sedimentation tank.

[0014] Thirdly, this application also provides a storage medium storing an executable program. When the executable program is executed by a processor, it implements the above-mentioned method for controlling the sludge discharge vehicle in a horizontal sedimentation tank.

[0015] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application, it can be implemented according to the contents of the specification. In order to make the above and other objects, features and advantages of this application more obvious and understandable, some embodiments are listed below for detailed description. Attached Figure Description

[0016] Figure 1 A top view of a sedimentation tank and a sludge removal vehicle according to at least one embodiment.

[0017] Figure 2 This is a front view of a sludge removal truck according to at least one embodiment.

[0018] Figure 3This is a flowchart of a sludge truck control method according to at least one embodiment.

[0019] Figure 4 This is a schematic diagram of a computer device according to at least one embodiment. Detailed Implementation

[0020] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, materials, apparatuses, steps, etc., can be employed. In other instances, well-known structures, methods, apparatuses, implementations, materials, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0023] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, or in one or more software-hardened modules, or in different network and / or processor devices and / or microcontroller devices.

[0024] In the traditional control of sludge discharge vehicles in horizontal flow sedimentation tanks, the sludge deposition distribution is affected by the coupling effect of water flow pattern and gravity settling, exhibiting nonlinear gradient characteristics. Traditional control methods only set three fixed travel speed levels (high, medium, and low), which cannot dynamically adjust the sludge discharge vehicle speed according to the real-time spatial distribution of sludge concentration, resulting in reduced sludge discharge efficiency and sludge residue problems.

[0025] To address the above issues, the inventors trained a sludge accumulation prediction model using multi-dimensional historical operating data accumulated over many years from sedimentation tanks in water plants. This model predicts the sludge gradient accumulation trend along the sedimentation tank, enabling self-learning and predictive pre-discharge sludge removal. Furthermore, by collecting real-time sludge concentration signals during discharge and eliminating on-site interference through digital filtering, an adaptive control strategy combining fuzzy control algorithm and maximum membership averaging method for fuzzy resolution is employed. This, combined with the real-time sludge concentration and the speed benchmark derived from the prediction model, dynamically optimizes and adjusts the sludge truck's speed. This "predictive benchmark setting + real-time fuzzy speed adjustment + fuzzy parameter optimization" linkage mechanism achieves an intelligent operation mode of low-speed full sludge removal for high sludge levels and high-speed rapid passage for low sludge levels. This enables adaptive intelligent sludge removal under all operating conditions, resolving the process pain points of sludge accumulation at the front and evacuation at the rear, while simultaneously ensuring stable effluent quality and energy conservation in equipment.

[0026] A schematic diagram of the horizontal flow sedimentation tank and sludge truck is shown below. Figure 1 and Figure 2 As shown. Figure 1 As shown, the sludge removal truck 20 spans the width of the horizontal flow sedimentation tank 10, while the length of the horizontal flow sedimentation tank 10 corresponds to the water flow direction (from left to right or from right to left). During sludge removal, the sludge removal truck 20 travels along the length of the horizontal flow sedimentation tank 10 while simultaneously using a sludge pump to remove sediment from the bottom of the tank. Figure 2 As shown, the sludge discharge truck 20 is equipped with several branch pipes 21 inserted into the bottom of the horizontal flow sedimentation tank 10. Each branch pipe 21 connects to the upper main pipe 22. The outer edge section 23 of the outer end of the main pipe 22 extends downwards to the sewage discharge channel outside the horizontal flow sedimentation tank 10. A sludge concentration meter 24 is installed at the port of the outer edge section 23 of the main pipe 22. The sludge concentration meter 24 is connected to a PLC controller 25 to transmit concentration signals, thus allowing the sludge discharge truck to monitor the sludge concentration in real time during operation. The PLC controller 25 is also connected to a frequency converter, which is connected to the travel motor of the sludge discharge truck 20, thereby adjusting the travel speed of the sludge discharge truck 20. In practice, changing the frequency of the frequency converter adjusts the travel speed of the sludge discharge truck 20.

[0027] One or more embodiments of this application provide a method for controlling a sludge discharge vehicle in a horizontal flow sedimentation tank, such as... Figure 3 As shown, it includes the following steps: Input real-time operational data into the siltation prediction model to obtain the predicted siltation distribution area, recommended sludge discharge interval, and predicted velocity benchmark value. The predicted siltation distribution area is divided into high siltation area, medium siltation area, and low siltation area. The predicted velocity benchmark value is divided into low velocity benchmark corresponding to high siltation area, medium velocity benchmark corresponding to medium siltation area, and high velocity benchmark corresponding to low siltation area. Start the sludge discharge vehicle when the recommended sludge discharge interval is met; The sludge discharge vehicle speed is adjusted according to the concentration fuzzy set to which the sludge concentration at the sludge discharge pipe outlet belongs. When the sludge concentration belongs to two adjacent concentration fuzzy sets, the sludge discharge vehicle speed is obtained by defuzzifying the fuzzy set using the membership function and the corresponding predicted speed benchmark value. When the sludge concentration belongs to only one concentration fuzzy set, the sludge discharge vehicle speed is the predicted speed benchmark value corresponding to that concentration fuzzy set.

[0028] The sludge deposition prediction model can employ common deep learning models, such as deep neural networks (DNN), convolutional neural networks (CNN), recurrent neural networks (RNN), or long short-term memory networks (LSTM). When training the sludge deposition prediction model, multi-dimensional historical operating data of the horizontal flow sedimentation tank is used as the input data source, with sludge distribution area, sludge discharge interval, and velocity baseline value as the output. Through iterative training, the converged prediction model can calculate the corresponding output results based on real-time operating conditions. When inputting real-time data, sedimentation tank staff can manually input various real-time operating data into the sludge deposition prediction model for calculation as needed, or the PLC controller can collect the real-time operating data and transmit it to the edge controller. The edge controller automatically inputs the real-time operating data into the sludge deposition prediction model for calculation at regular intervals (e.g., 10 minutes, 30 minutes, or 60 minutes).

[0029] The predicted siltation distribution area is a region divided by the predicted siltation at the bottom of the horizontal flow sedimentation tank output by the prediction model. It includes the predicted location distribution of high, medium and low siltation zones along the sedimentation tank and the predicted sludge concentration in each siltation zone, so as to guide the sludge removal truck to carry out targeted operations.

[0030] The recommended sludge discharge interval is a time result output by the prediction model, reflecting the estimated time for sludge to reach the allowable deposition thickness under current operating conditions. The PLC controller calculates the remaining time until the next sludge discharge based on the recommended sludge discharge interval compared to the already downtime.

[0031] The predicted speed baseline is the speed result output by the prediction model. It is a recommended initial driving speed reference value for sludge removal trucks based on the predicted siltation distribution area. These speed baseline values ​​usually correspond to different siltation areas. For example, high siltation areas correspond to low speed baselines, medium siltation areas correspond to medium speed baselines, and low siltation areas correspond to high speed baselines, so as to achieve effective sludge removal in different areas.

[0032] The sludge accumulation prediction model can control the output strategy based on real-time influent load: During the rainy season, when the influent volume is large and the turbidity is high, the sludge accumulation rate increases, and the predicted speed baseline values ​​(including high speed, medium speed, and low speed) output by the model will decrease. The recommended sludge discharge interval will be shortened to ensure better sludge discharge effect. When the influent volume is small and the influent turbidity is low, the sludge accumulation rate usually slows down, and the predicted speed baseline values ​​(including high speed, medium speed, and low speed) output will increase. The recommended sludge discharge interval will be increased to reduce the number of sludge discharges and reduce equipment operating energy consumption and water suction volume. Simultaneously, the sludge accumulation prediction model also outputs a sludge concentration prediction curve along the sedimentation tank, dividing it into three sludge accumulation zones and matching them with a pre-set speed benchmark: the first zone is marked as a high sludge accumulation zone, predicting that the sludge concentration will be high for a long time and triggering sludge discharge after reaching the sludge accumulation threshold. The high sludge accumulation zone is matched with a low-speed benchmark value, allowing sufficient time for slow sludge discharge to thoroughly remove the thick layer of sludge; the middle zone is marked as a medium sludge accumulation zone, with a moderate amount of sludge settling, matched with a medium-speed benchmark, balancing sludge discharge effect and operational efficiency; the last zone is marked as a low sludge accumulation zone, predicting that there is very little sludge at the bottom of the tank in this area, matched with a high-speed benchmark, allowing the sludge truck to quickly pass through this area, reducing surface disturbance and reducing ineffective energy consumption.

[0033] The sludge removal crane is activated when the recommended sludge removal interval is met. In one implementation, after obtaining the recommended sludge removal interval, the remaining time until the next sludge removal is calculated. The timer starts counting from the remaining time until it reaches zero, at which point the start command for the sludge removal crane is automatically triggered. In other implementations, the sludge removal crane can also be started manually. For example, once the operator confirms that the recommended sludge removal interval has been reached, they can manually press the start button to begin operation.

[0034] The sludge discharge vehicle speed is adjusted based on the fuzzy set of sludge concentration at the sludge discharge pipe inlet. In one implementation, an online sludge concentration detection device is installed at the sludge discharge pipe inlet to monitor the sludge concentration in the discharged water flow in real time. The acquired sludge concentration value is compared with multiple fuzzy sets of concentration, for example, the fuzzy sets are divided into three intervals: "low," "medium," and "high," each interval corresponding to a fixed speed adjustment strategy. When the sludge concentration belongs to only one fuzzy set of concentration, for example, if the sludge concentration is clearly in the "low" concentration interval, the sludge discharge vehicle speed directly adopts the predicted speed benchmark value corresponding to that fuzzy set. For example, if the "low" concentration fuzzy set corresponds to a high-speed benchmark, the sludge discharge vehicle operates at the high-speed benchmark. When the sludge concentration belongs to two adjacent fuzzy concentration sets, for example, when the sludge concentration belongs to both the "low" and "medium" concentration ranges, the membership function is used in conjunction with the predicted speed benchmark values ​​corresponding to the "low" and "medium" concentration ranges to perform defuzzification calculation to determine the sludge discharge vehicle speed. This speed will be between the high-speed benchmark and the medium-speed benchmark. On the one hand, this makes the change in the sludge discharge vehicle speed smoother, and on the other hand, the sludge discharge vehicle speed is more in line with the real-time concentration situation, taking into account both the sludge discharge effect and better energy efficiency.

[0035] Therefore, the sludge discharge vehicle control method of the embodiment dynamically generates a sludge discharge strategy through a sludge accumulation prediction model, and combines fuzzy control of sludge concentration to achieve adaptive adjustment of the sludge discharge vehicle speed. It can dynamically adjust the sludge discharge vehicle speed according to the real-time sludge distribution and sludge concentration, avoid poor sludge discharge effect in high sludge accumulation areas and energy waste in low sludge accumulation areas, improve sludge discharge efficiency and effect, and help improve the operational stability of the sedimentation tank.

[0036] In at least one embodiment, the real-time operational data input to the sludge accumulation prediction model includes: total influent volume, influent turbidity, effluent turbidity, and shutdown interval duration. Specifically, the total influent volume refers to the total amount of water entering the horizontal flow sedimentation tank between the last sludge truck shutdown and the data input to the model. It is a key parameter reflecting the influent load of the sedimentation tank and directly affects the settling amount of suspended solids and the sludge accumulation rate. This data can be monitored and accumulated in real time using a flow meter installed on the influent pipe. Influent turbidity refers to the degree of turbidity of the influent to the horizontal flow sedimentation tank. It directly characterizes the content of suspended solids in the raw water and is the main material basis for sludge formation. Influent turbidity can be continuously measured using an online turbidity sensor on the influent pipe. Effluent turbidity refers to the degree of turbidity of the effluent after treatment in the horizontal flow sedimentation tank. It indirectly reflects the settling efficiency of the sedimentation tank and the settling state of the sludge. Abnormal effluent turbidity may indicate insufficient sludge settling or that some sludge is carried out with the water flow. The turbidity of the effluent can be monitored in real time by installing an online turbidity sensor at the outlet of the sedimentation tank. The stopping interval refers to the length of time the sludge truck stops operating. During this period, the sludge at the bottom of the sedimentation tank will continue to settle and accumulate naturally. The length of this period directly affects the thickness and density of the sludge accumulation. The stopping interval can be automatically recorded in the log of the sludge truck's control system or accurately measured by an independent timing module.

[0037] These data, serving as input features for the model, provide rich operational information. For example, high influent turbidity and longer stopping intervals typically predict faster sludge accumulation rates and larger sludge volumes, while the total influent volume and effluent turbidity further refine the impact of hydraulic conditions and settling effects on sludge accumulation. Based on this multi-dimensional data, the sludge accumulation prediction model can more accurately output predicted sludge distribution areas, recommended sludge discharge intervals, and predicted speed baselines, thus providing a more reliable and refined basis for subsequent adjustments to sludge discharge vehicle speeds.

[0038] By employing the aforementioned technical solution, the total influent volume, influent turbidity, effluent turbidity, and shutdown interval duration are used as real-time operational data. This allows the model to more comprehensively and accurately capture the dynamic changes in sludge accumulation within the horizontal flow sedimentation tank. This significantly improves the model's prediction accuracy and robustness, making the predicted sludge distribution area, recommended sludge discharge interval, and predicted speed baseline values ​​closer to actual conditions. Consequently, the adjustment of the sludge discharge vehicle speed can more precisely match the sludge accumulation state within the sedimentation tank, avoiding insufficient or excessive sludge discharge due to insufficient or inaccurate data, effectively improving sludge discharge efficiency and the operational stability of the sedimentation tank.

[0039] In at least one embodiment, the concentration fuzzy set is divided into low-concentration, medium-concentration, and high-concentration subsets, with overlap between the low-concentration and medium-concentration subsets, and between the high-concentration and medium-concentration subsets. This division into low-concentration, medium-concentration, and high-concentration subsets is intended to more finely characterize different levels of sludge concentration, thereby providing a more discriminative input for subsequent adjustments to the sludge discharge vehicle speed. This division can be based on expert experience, historical operational data analysis, or optimized using machine learning algorithms. For example, different concentration thresholds can be set to initially define these subsets based on the operating characteristics of the sedimentation tank and the physicochemical properties of the sludge. The overlapping regions between fuzzy subsets allow a specific sludge concentration value to belong to multiple fuzzy subsets simultaneously. This overlapping design avoids the abrupt changes at the boundaries caused by traditional precise set partitioning, which can lead to sudden changes in the sludge discharge vehicle speed and subsequent shocks.

[0040] The high-concentration subset corresponds to the low-speed baseline, the medium-concentration subset to the medium-speed baseline, and the low-concentration subset to the high-speed baseline. High-concentration sludge typically indicates a large buildup, requiring the sludge truck to operate at a lower speed to ensure adequate scraping and removal. Medium-concentration sludge corresponds to a medium speed to balance removal efficiency and energy consumption. Low-concentration sludge allows the sludge truck to operate at a higher speed to improve removal efficiency and reduce energy consumption. This mapping achieves a balance between sludge removal efficiency and operating energy consumption.

[0041] In at least one embodiment, when the sludge concentration simultaneously belongs to two adjacent fuzzy concentration sets, the sludge discharge vehicle speed is obtained by defuzzifying the fuzzy state using a membership function combined with the corresponding predicted velocity benchmark value, including: When the sludge concentration belongs to two adjacent fuzzy concentration sets at the same time, the membership degree of the sludge concentration to each fuzzy concentration set is calculated using the triangular membership function, and then the sludge discharge vehicle speed is calculated using the maximum membership average method.

[0042] The triangular membership function is a fuzzy mathematics tool used to quantify the degree to which a precise numerical value (the sludge concentration at the sludge discharge pipe inlet) belongs to a certain fuzzy set (a low-concentration subset, a medium-concentration subset, and a high-concentration subset). The triangular membership function defines membership by a triangular-shaped function, such that the membership degree is 1 at the center of the fuzzy set and gradually decreases to 0 at the boundaries. Other implementations besides the triangular membership function include trapezoidal membership functions, Gaussian membership functions, and sigmoid membership functions to describe the degree to which the sludge concentration belongs to fuzzy sets of different concentrations.

[0043] The maximum membership averaging method is a defuzzification method that converts the result of fuzzy inference (i.e., the membership degree of sludge concentration to different concentration fuzzy sets) into a precise output value (i.e., the sludge discharge vehicle speed). The maximum membership averaging method obtains a comprehensive and continuous output by weighted averaging of the membership degrees of each fuzzy set. In other implementations, besides the maximum membership averaging method, other defuzzification methods such as the centroid method or the median method can also be used to calculate the sludge discharge vehicle speed.

[0044] By introducing triangular membership functions and the maximum membership averaging method, the problem of accurately determining the sludge discharge vehicle speed when the sludge concentration simultaneously belongs to two adjacent fuzzy sets of concentration is effectively solved. This method yields a smooth, continuous, and accurate sludge discharge vehicle speed, rather than simply selecting a fixed speed benchmark value. This mechanism ensures that the sludge discharge vehicle speed can be continuously adjusted according to subtle changes in sludge concentration, avoiding sudden changes or oscillations in speed that may occur at fuzzy set boundaries, thus making the sludge discharge process more stable and efficient. This scheme enables the sludge discharge process to more intelligently adapt to dynamic changes in sludge concentration, ensuring stable sludge discharge efficiency and sedimentation tank effluent quality, while also helping to extend the service life of the sludge discharge equipment.

[0045] In at least one embodiment, a triangular membership function is used to calculate the membership degree of the sludge concentration to each concentration fuzzy set: When a≤x≤m, then μ(x)=(xa) / (ma), When m ≤ x ≤ b, then μ(x) = (bx) / (bm). When x b, then μ(x) = 0; Where μ(x) is the membership degree, x is the sludge concentration at the sludge discharge pipe inlet, a is the minimum value of the concentration fuzzy set, m is the median value of the concentration fuzzy set, and b is the maximum value of the concentration fuzzy set.

[0046] The triangular membership function calculates the membership value μ(x) of a concentration fuzzy set for a given input value (e.g., the sludge concentration x at the sludge discharge pipe inlet). This function is constructed by defining three key parameters—a (minimum), m (intermediate), and b (maximum)—which together determine the boundaries and center of the fuzzy set. When the input value x is in the interval [a, m], the membership value μ(x) increases linearly with x; when x is in the interval [m, b], the membership value μ(x) decreases linearly with x; and when x exceeds the interval [a, b], the membership value μ(x) is set to 0, indicating that the input value does not belong to the fuzzy set at all.

[0047] The membership degree μ(x) represents the degree to which sludge concentration x belongs to a specific concentration fuzzy set (such as a low-concentration subset, a medium-concentration subset, or a high-concentration subset), and its value typically ranges from 0 to 1. The sludge concentration x at the sludge discharge pipe inlet is the sludge concentration value monitored in real time by an online sludge concentration detection device installed at the sludge discharge pipe inlet. Its accuracy directly affects the subsequent membership degree calculation and the adjustment of the sludge discharge vehicle speed. The minimum value a, the median value m, and the maximum value b of the concentration fuzzy set are the key parameters for defining each concentration fuzzy set. They together determine the shape of the membership function and the range of the fuzzy set. The setting of these parameters can be derived based on actual operating experience and expert knowledge.

[0048] During implementation, the measured values ​​of the online sludge concentration detection device (i.e., sludge concentration meter) at the sludge discharge pipe outlet are easily affected by water disturbance, air bubbles, and vibration of the sludge scraping machinery, resulting in spike interference. Therefore, the collected sludge concentration can first be filtered by moving average, and multiple sets of concentration values ​​can be collected continuously and averaged to eliminate instantaneous pulse interference. The messy original signal is first transformed into a stable and reliable effective signal before membership calculation is performed.

[0049] In at least one embodiment, in the low concentration subset, a=0, m=0.07, b=0.14; in the medium concentration subset, a=0.1, m=0.2, b=0.3; and in the high concentration subset, a=0.25, m=0.625, b=1.

[0050] Here, parameter 'a' represents the lowest concentration value at which the fuzzy set of concentration begins to have membership, parameter 'b' represents the highest concentration value at which the membership of the fuzzy set of concentration drops to zero, and parameter 'm' represents the concentration value at which the membership of the fuzzy set of concentration reaches its maximum value (usually 1). The setting of these parameters provides a quantitative basis for the subsequent accurate calculation of the membership of any given sludge concentration. These parameters can be statistically analyzed and optimized based on a large amount of historical operating data to reflect the distribution characteristics of sludge concentration under actual operating conditions; alternatively, they can be set through expert experience and on-site commissioning, combined with the characteristics of the sedimentation tank and sludge discharge requirements.

[0051] In at least one embodiment, the sludge discharge vehicle speed is calculated using the maximum membership degree averaging method: Uout=(μ L (x)*f L +μ M (x)*f M +μ H (x)*f H ) / (μ L (x)+μ M (x)+μ H (x)) Where Uout is the output sludge discharge vehicle speed, μ L(x) represents the membership degree of the low-concentration subset, μ M (x) represents the membership degree of the medium-concentration subset, μ H (x) represents the membership degree of the high-concentration subset, f L For the high-speed benchmark corresponding to the low-concentration subset, f M f is the medium-velocity baseline corresponding to the medium-concentration subset. H This represents the low-speed baseline corresponding to the high-concentration subset. The speed regulation of sludge removal trucks is generally achieved by adjusting the frequency of the frequency converter; therefore, Uout and f here... L f M f H All values ​​are frequency values, and their units are all Hz.

[0052] Among them, the maximum membership averaging method is a defuzzification method that converts the result of fuzzy inference (i.e., the membership degree of sludge concentration to different fuzzy sets) into a precise output value (i.e., the sludge discharge vehicle speed). The maximum membership averaging method calculates the final output by weighted averaging of the membership degree of each fuzzy set and its corresponding output value. This comprehensively considers the membership degree of sludge concentration in different fuzzy sets, thus obtaining a smooth and continuous sludge discharge vehicle speed, avoiding sudden changes in the sludge discharge vehicle speed, and improving stability.

[0053] Uout represents the output speed of the sludge discharge vehicle, which is the final speed obtained after fuzzy defuzzification calculation. It is the actual operating speed of the sludge discharge vehicle as instructed by the control system. Uout is input to the frequency converter of the sludge discharge vehicle, which drives the sludge discharge vehicle to move at the corresponding speed, so as to move in the sedimentation tank at an appropriate rate to achieve efficient and stable sludge discharge operation.

[0054] μ L (x) represents the membership degree of the low-concentration subset, μ M (x) represents the membership degree of the medium-concentration subset, μ H (x) represents the membership degree of the high-concentration subset. These membership degree values ​​indicate the degree to which the current sludge concentration x at the sludge discharge port belongs to the low-concentration, medium-concentration, and high-concentration subsets, respectively. They are real numbers between 0 and 1, where 1 represents complete membership and 0 represents no membership at all. These membership degrees are weighting factors in the defuzzification process, quantifying the degree of correlation between the current sludge concentration and different concentration fuzzy sets, thereby guiding the direction and magnitude of the adjustment of the sludge discharge vehicle speed. These membership values ​​can be calculated based on the real-time sludge concentration x using predefined membership functions (such as triangular, trapezoidal, Gaussian, etc.).

[0055] f L For the high-speed benchmark corresponding to the low-concentration subset, f M f is the medium-velocity baseline corresponding to the medium-concentration subset. HThese are low-speed benchmarks corresponding to high-concentration subsets. These benchmark speed values ​​are reference speeds output by the sludge accumulation prediction model and associated with fuzzy sets of different concentrations. They represent the recommended speeds that sludge discharge vehicles should take under ideal conditions when the sludge concentration belongs entirely to a specific concentration subset.

[0056] The Uout calculation formula ensures that when the sludge concentration falls within the overlapping region of different concentration fuzzy sets, the sludge discharge vehicle speed can smoothly transition between different baseline speeds, avoiding abrupt speed changes. For example, when the sludge concentration mainly belongs to the low-concentration subset, μ L (x) will be larger, and Uout will be closer to f. L When the sludge concentration is between low and medium, Uout will be f. L and f M The weighted average value is used. This precise weighted average mechanism allows the adjustment of the sludge discharge vehicle speed to fully reflect subtle changes in real-time sludge concentration, thereby achieving refined control of the sludge discharge vehicle.

[0057] In at least one embodiment, the method for controlling the sludge discharge vehicle in a horizontal flow sedimentation tank further includes: training a sludge accumulation prediction model based on historical sludge discharge operating data, wherein the historical sludge discharge operating data includes: total influent volume during intervals, influent turbidity during intervals, effluent turbidity during intervals, stopping interval duration, high-speed benchmark for vehicle operation, sludge concentration during high-speed operation, duration of high-speed operation, medium-speed benchmark for vehicle operation, sludge concentration during medium-speed operation, duration of medium-speed operation, low-speed benchmark for vehicle operation, sludge concentration during low-speed operation, and duration of low-speed operation.

[0058] Furthermore, when training the sludge deposition prediction model, the speed reference range of the prediction model's output is limited to ensure that the speed reference output by the prediction model matches the performance of the sludge removal truck itself. Specifically, the low-speed reference range is 30Hz to 35Hz, the medium-speed reference range is 40Hz to 45Hz, and the high-speed reference range is 50Hz to 60Hz.

[0059] By utilizing historical operational and sludge discharge data, the sludge accumulation prediction model is learned and optimized to better capture its inherent patterns, thereby improving the accuracy and reliability of predictions. Historical sludge discharge data refers to multi-dimensional parameter records reflecting the system state and sludge discharge effect accumulated during the actual operation and sludge discharge process of the horizontal flow sedimentation tank, serving as the foundation for deep learning training of the model. Historical sludge discharge data can be obtained from the automated monitoring system during the sedimentation tank's operation.

[0060] "Total influent volume during the interval, influent turbidity during the interval, effluent turbidity during the interval, and stop interval duration" are parameters reflecting the influent load and water quality characteristics of the sedimentation tank. "High-speed benchmark, sludge concentration during high-speed operation, duration of high-speed operation, medium-speed benchmark, sludge concentration during medium-speed operation, duration of medium-speed operation, low-speed benchmark, sludge concentration during low-speed operation, and duration of low-speed operation" are parameters reflecting the actual sludge removal effect of the sludge removal truck under different operating strategies.

[0061] By analyzing historical data, the predictive model establishes a complex mapping relationship between environmental factors, sludge truck operation strategies, actual sludge accumulation areas, recommended sludge discharge intervals, and predicted speed baselines. This training based on actual operational experience transforms the predictive model from a general algorithm into an intelligent predictor optimized for the specific operational characteristics of a horizontal flow sedimentation tank. Once trained and deployed, the model can more accurately predict sludge accumulation areas, recommended sludge discharge intervals, and predicted speed baselines based on real-time operational data, providing a more precise and reliable basis for subsequent sludge truck initiation and speed adjustments. This training mechanism ensures that the predictive model's output better adapts to changes in actual operating conditions, thereby improving the intelligence level and sludge discharge efficiency of the entire sludge truck control method.

[0062] The following example illustrates the mud truck control method of this application.

[0063] The real-time operating data of the horizontal flow sedimentation tank was input into the sludge accumulation prediction model. The output results were: low speed baseline 33Hz, medium speed baseline 44Hz, high speed baseline 54Hz, and the recommended sludge discharge interval was 3h. The first third was the high sludge accumulation zone, the middle third was the medium sludge accumulation zone, and the last third was the low sludge accumulation zone.

[0064] In the low-concentration subset, a=0, m=0.07, b=0.14; in the medium-concentration subset, a=0.1, m=0.2, b=0.3; in the high-concentration subset, a=0.25, m=0.625, b=1.

[0065] 1.2 hours have passed since the last sludge discharge, therefore the remaining time until the next sludge discharge is 1.8 hours. The sludge discharge truck will begin operation when the remaining time reaches zero. Initially, the truck is in the high-sludge accumulation zone, and the inverter frequency is set to the low-speed baseline of 33Hz. The truck's speed is then adjusted based on the real-time sludge concentration at the discharge port. For example, when the truck passes between the high and medium-sludge accumulation zones, the real-time sludge concentration x = 0.27, and the following calculations are performed: Membership degree of low-concentration subsets: μ L (0.27) = 0 Membership degree of medium concentration subsets: μ M (0.27) = (0.3 - 0.27) / (0.3 - 0.2) = 0.3 Membership degree of high-concentration subsets: μ H (0.27) = (0.27 - 0.25) / (0.625 - 0.25) = 0.053 Calculation using the maximum membership degree average method: Uout=(0*54+0.3*44+0.053*33) / (0.3+0.053)=42.35Hz Therefore, the frequency of the inverter was adjusted to 42.35Hz to control the sludge truck to travel at the corresponding speed.

[0066] For example, when the sludge truck passes between the medium-sludge accumulation zone and the low-sludge accumulation zone, if the real-time sludge concentration x = 0.12, then the following calculations are performed: Membership degree of low-concentration subsets: μ L (0.12) = (0.14 - 0.12) / (0.14 - 0.07) = 0.286 Membership degree of medium concentration subsets: μ M (0.12) = (0.12 - 0.1) / (0.2 - 0.1) = 0.2 Membership degree of high-concentration subsets: μ H (0.12) = 0 Calculation using the maximum membership degree average method: Uout=(0.286*54+0.2*44+0*33) / (0.286+0.2)=49.88Hz Therefore, the frequency of the inverter was adjusted to 49.88Hz to control the sludge truck to travel at the corresponding speed.

[0067] The sludge discharge vehicle control method for horizontal flow sedimentation tanks proposed in this application constructs a predictive model to output predicted speed benchmarks and sludge discharge intervals. Combined with real-time fuzzy speed regulation, it specifically addresses the process defect of the traditional sludge discharge vehicle's fixed three-stage constant speed operation being mismatched with the gradient sludge accumulation along the sedimentation tank. It requires minimal structural modifications to the sludge discharge vehicle and the horizontal flow sedimentation tank, only necessitating the addition of an online sludge concentration detection device at the sludge discharge pipe inlet. No water outages are required, and existing PLC controllers, frequency converters, edge controllers, and other hardware can be fully reused, resulting in low overall investment costs and ease of implementation.

[0068] The sludge discharge vehicle control method for horizontal flow sedimentation tanks in this application forms a two-level coordinated control logic: The first stage involves pre-processing deep learning model prediction and control. It continuously collects real-time operational data and uploads it to the edge controller. The prediction model autonomously completes training and computation, outputting the locations of high, medium, and low sludge integration zones in the sedimentation tank, the recommended sludge discharge interval, and dynamically distributing predicted speed baseline values. Therefore, the sludge discharge cycle can be automatically lengthened or shortened according to different seasons / weather conditions, which helps reduce unnecessary start-stops and idle energy consumption of the sludge discharge truck. Furthermore, pre-determining the speed range for each zone reduces the frequency of frequent speed adjustments during sludge discharge truck operation, resulting in smoother equipment operation.

[0069] The second stage involves real-time fuzzy adaptive speed control. During the sludge truck's operation, an online sludge concentration detection device collects real-time sludge concentration signals. After filtering to eliminate data interference, the signals are compared with a fuzzy concentration set for membership degree calculation. A triangular membership function is used to calculate the membership degree, and the maximum membership degree average method is used to defuzzify the calculation and obtain an accurate speed value (frequency value). Within a given speed range, the inverter output frequency is smoothly and continuously adjusted to achieve slow driving for sufficient sludge suction in high-sludge conditions and rapid passage in low-sludge conditions, ensuring a balance between sludge discharge and optimized energy consumption. Simultaneously, the on-site measured sludge concentration, vehicle speed, and water quality data are fed back to the sludge accumulation prediction model for continuous iterative optimization and training, enabling it to have long-term self-learning capabilities without requiring repeated manual adjustments of control parameters on-site.

[0070] The control method for the sludge removal vehicle in the horizontal flow sedimentation tank can adapt to fluctuations in influent water quality around the clock, stabilize the effluent water quality of the sedimentation tank, effectively reduce the filtration load of downstream filters, and reduce the water consumption for backwashing of filters; at the same time, it significantly reduces the energy consumption of the sludge removal vehicle during ineffective driving and the amount of sludge pumped, and comprehensively improves the automation level, operational stability and overall energy-saving benefits of the sludge removal process in the horizontal flow sedimentation tank.

[0071] At least one embodiment of this application is a computer device, such as... Figure 4 As shown, the computer device 50 includes a processor 51, a memory 52, and a computer program 53 stored in the memory 52 and executable on the processor. When the processor 51 executes the computer program 53, it implements the sludge truck control method of one or more embodiments described above. By deploying the sludge truck control method described above on the computer device 50, the automated and efficient execution of the sludge truck control method of this application is achieved.

[0072] Computer device 50 refers to an electronic device capable of executing instructions, processing data, and storing information. It can be a general-purpose computer system, such as a personal computer, server, or workstation, or an embedded system, edge controller, or dedicated computing platform customized for a specific application. This device provides the necessary hardware foundation and operating environment for complex computing tasks.

[0073] Computer device 50 can also communicate with one or more external devices (e.g., keyboard, pointing device, Bluetooth device, wired terminal, etc.), and with one or more devices that enable a user to interact with computer device 50, and / or with any device that enables computer device 50 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interfaces. Furthermore, computer device 50 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via a network adapter. The network adapter communicates with other modules of computer device 50 via a bus. It should be understood that other hardware and / or software modules can be used in conjunction with computer device 50, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0074] Processor 51 is the core computing unit of computer device 50, responsible for interpreting and executing instructions in computer programs, performing arithmetic and logical operations, and data processing. Processor 51 can be a central processing unit (CPU) for general computing and control tasks; it can also be a graphics processing unit (GPU), which excels at parallel computing, especially suitable for training and inference of deep learning models; or it can be a field-programmable gate array (FPGA) or application-specific integrated circuit (ASIC) for implementing highly optimized specific algorithms.

[0075] Memory 52 is a hardware component used to store data and computer programs 53. Memory 52 may include random access memory (RAM) for temporary storage of running programs and data for fast access by the processor; it may also include read-only memory (ROM) or non-volatile memory (such as solid-state drives (SSDs), hard disk drives (HDDs), or flash memory) for long-term storage of the operating system, applications, and large amounts of data.

[0076] The computer program 53, stored in memory 52 and executable on the processor, is a collection of instructions stored in memory 52 in a form that can be understood and executed by the processor 51. When the processor 51 loads and executes these instructions, it operates according to a predetermined logical flow. This program can be an executable file compiled from a high-level language, interpreted code written in a scripting language, or low-level instructions existing as firmware. When the processor 51 runs according to the instructions of the computer program 53 stored in memory 52, it executes the steps and operations defined by the program one by one. The processor 51 is responsible for coordinating data flow, performing computational tasks, and managing storage resources, thereby fully realizing all aspects of the sludge truck control method.

[0077] Through the description of the above embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, portable hard drive, etc.) or on a network, including several instructions to cause a computer device 50 to execute the sludge truck control method according to the embodiments of this application.

[0078] At least one embodiment of this application is a storage medium storing an executable program. When the executable program is executed by a processor, it implements the sludge truck control method of the above embodiments. When the executable program is run, the program code causes the processor to perform the steps described in this specification according to the various exemplary embodiments of this application.

[0079] Storage media are physical media capable of storing digital data or instructions that can be read and executed by a computer system. This media can be non-volatile, such as hard disk drives (HDDs), solid-state drives (SSDs), flash memory, or optical discs (CD-ROMs, DVD-ROMs), used for long-term storage of executable programs. Alternatively, it can be volatile, such as random access memory (RAM), used for temporary storage of instructions and data during program execution.

[0080] An executable program is a collection of instructions that, after being compiled or interpreted, can be directly executed by a computer's processor to complete the various tasks of the sludge truck control method. This program can be written in a high-level programming language (such as Python, C++, MATLAB, etc.).

[0081] A processor is the core component of a computer system, responsible for reading and executing instructions from computer programs to perform arithmetic, logical, and control operations. This processor can be a central processing unit (CPU), providing general-purpose computing power; it can be a graphics processing unit (GPU), particularly suitable for massively parallel computing tasks in deep learning to accelerate the training and inference processes of neural networks; or it can be an application-specific integrated circuit (ASIC) or a field-programmable gate array (FPGA), optimized for specific computing tasks.

[0082] It should be understood that other embodiments of this application will readily conceive of by those skilled in the art upon consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. This application is not limited to the methods / structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The specification and embodiments are to be considered exemplary only, and the scope of this application is defined only by the appended claims.

Claims

1. A method for controlling a sludge discharge vehicle in a horizontal flow sedimentation tank, characterized in that, It includes the following steps: Input real-time operational data into the siltation prediction model to obtain the predicted siltation distribution area, recommended sludge discharge interval, and predicted velocity benchmark value; wherein, the predicted siltation distribution area is divided into high siltation area, medium siltation area, and low siltation area, and the predicted velocity benchmark value is divided into low velocity benchmark corresponding to high siltation area, medium velocity benchmark corresponding to medium siltation area, and high velocity benchmark corresponding to low siltation area. Start the sludge discharge vehicle when the recommended sludge discharge interval is met; The sludge discharge vehicle speed is adjusted according to the concentration fuzzy set to which the sludge concentration at the sludge discharge pipe outlet belongs. When the sludge concentration belongs to two adjacent concentration fuzzy sets, the sludge discharge vehicle speed is obtained by defuzzifying the fuzzy set using the membership function and the corresponding predicted speed benchmark value. When the sludge concentration belongs to only one concentration fuzzy set, the sludge discharge vehicle speed is the predicted speed benchmark value corresponding to that concentration fuzzy set.

2. The method for controlling the sludge discharge vehicle in a horizontal flow sedimentation tank as described in claim 1, characterized in that, The real-time operational data input to the siltation prediction model includes: total influent volume, influent turbidity, effluent turbidity, and shutdown interval duration.

3. The method for controlling the sludge discharge vehicle in a horizontal flow sedimentation tank as described in claim 1, characterized in that, The concentration fuzzy set is divided into a low-concentration subset, a medium-concentration subset, and a high-concentration subset. The low-concentration subset overlaps with the medium-concentration subset, and the high-concentration subset overlaps with the medium-concentration subset. The high-concentration subset corresponds to the low-speed reference, the medium-concentration subset corresponds to the medium-speed reference, and the low-concentration subset corresponds to the high-speed reference.

4. The method for controlling the sludge discharge vehicle in a horizontal flow sedimentation tank as described in claim 3, characterized in that, When the sludge concentration belongs to two adjacent fuzzy concentration sets simultaneously, the sludge discharge vehicle speed is obtained by defuzzifying the fuzzy set using a membership function combined with the corresponding predicted speed benchmark value, including: When the sludge concentration belongs to two adjacent fuzzy concentration sets at the same time, the membership degree of the sludge concentration to each fuzzy concentration set is calculated using the triangular membership function, and then the sludge discharge vehicle speed is calculated using the maximum membership average method.

5. The method for controlling the sludge discharge vehicle in a horizontal flow sedimentation tank as described in claim 4, characterized in that, The membership degree of sludge concentration to each concentration fuzzy set is calculated using a triangular membership function: When a≤x≤m, then μ(x)=(xa) / (ma), When m ≤ x ≤ b, then μ(x) = (bx) / (bm). When x b, then μ(x) = 0; Where μ(x) is the membership degree, x is the sludge concentration at the sludge discharge pipe inlet, a is the minimum value of the concentration fuzzy set, m is the median value of the concentration fuzzy set, and b is the maximum value of the concentration fuzzy set.

6. The method for controlling the sludge discharge vehicle in a horizontal flow sedimentation tank as described in claim 5, characterized in that, In the low concentration subset, a=0, m=0.07, b=0.14; in the medium concentration subset, a=0.1, m=0.2, b=0.3; in the high concentration subset, a=0.25, m=0.625, b=1.

7. The method for controlling the sludge discharge vehicle in a horizontal flow sedimentation tank as described in claim 4, characterized in that, The sludge discharge vehicle speed is calculated using the maximum membership degree average method. Uout=(μ L (x)*f L +m M (x)*f M +m H (x)*f H ) / (m L (x)+μ M (x)+μ H (x)) Where Uout is the output sludge discharge vehicle speed, μ L (x) represents the membership degree of the low-concentration subset, μ M (x) represents the membership degree of the medium-concentration subset, μ H (x) represents the membership degree of the high-concentration subset, f L For the high-speed benchmark corresponding to the low-concentration subset, f M f is the medium-velocity baseline corresponding to the medium-concentration subset. H This is the low-speed benchmark corresponding to the high-concentration subset.

8. The method for controlling the sludge discharge vehicle in a horizontal flow sedimentation tank as described in claim 1, characterized in that, Also includes: A sludge accumulation prediction model is trained based on historical sludge discharge operation data, which includes: total influent volume at intervals, influent turbidity at intervals, effluent turbidity at intervals, stopping interval duration, high-speed benchmark for vehicle operation, sludge concentration at high-speed operation, duration of high-speed operation, medium-speed benchmark for vehicle operation, sludge concentration at medium-speed operation, duration of medium-speed operation, low-speed benchmark for vehicle operation, sludge concentration at low-speed operation, and duration of low-speed operation.

9. A computer device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the sludge discharge vehicle control method for a horizontal flow sedimentation tank as described in any one of claims 1 to 8.

10. A storage medium, characterized in that, The storage medium stores an executable program, which, when executed by a processor, implements the sludge discharge vehicle control method for a horizontal sedimentation tank as described in any one of claims 1 to 8.

Images