An intelligent control operation method and system for a filter press

Abstract

The application discloses an intelligent control operation method and system for a filter press, and relates to the technical field of intelligent control. The method comprises the following steps: acquiring the real-time viscosity and real-time concentration of the slurry entering the filter press during operation and the change rate curve of the filtrate flow, using a digital twin model to real-time back-calculate the average specific resistance value and filter cake prediction parameters of the current filtration process, real-time determining the filtration stage, and dynamically generating a control instruction sequence based on the average specific resistance value, filter cake prediction parameters and filtration stage; during the execution of the control instruction sequence, real-time monitoring the parameter deviation between the actual operation parameters of the filter press and the instruction preset operation parameters; when the parameter deviation is less than a preset deviation threshold, the system automatically performs self-healing control to maintain the normal operation of the filter press. In this way, the problem of unstable filter cake parameters and unplanned shutdown of traditional filter presses caused by parameter solidification can be effectively solved, thereby significantly improving the reliability and intelligent level of equipment operation.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and in particular to an intelligent control operation method and system for a filter press. Background Technology

[0002] Filter presses, as a mature solid-liquid separation device, are widely used in mining, chemical, and environmental protection fields. In related technologies, filter press control systems are mostly based on programmable logic controllers (PLCs), typically using preset time-pressure curves for control. However, due to the fluctuations in the viscosity, concentration, and other physical properties of the feed slurry, fixed control curves often cannot adapt to actual working conditions, leading to unstable filter cake moisture content, excessive energy consumption, or filter cloth clogging.

[0003] To monitor the actual operating conditions of filter presses in real time, digital twin technology has been introduced. However, this technology mainly focuses on 3D visualization and offline simulation. The digital twin model serves only as a data display window and does not deeply participate in real-time control decisions. Furthermore, the technology lacks effective online inversion methods for key physical parameters inside the filter press, making it difficult to dynamically adjust the pressing strategy based on the actual formation state of the filter cake. In addition, during the pressing process, slight deviations often occur due to factors such as residue inclusions on the filter plate sealing surface. The technology typically issues direct warnings and shutdowns for such faults, resulting in unqualified moisture content in the current batch of filter cake or unplanned shutdowns, severely impacting the overall efficiency of the equipment. Summary of the Invention

[0004] This application provides an intelligent control operation method and system for a filter press, which solves the following technical problem: how to effectively solve the problem of unstable filter cake parameters and unplanned downtime caused by fixed parameters in traditional filter presses, and significantly improve the reliability and intelligence level of equipment operation.

[0005] In a first aspect, embodiments of this application provide an intelligent control operation method for a filter press, the method comprising: Acquire the operating status data of the filter press during its operation; Based on the real-time viscosity and concentration of the feed slurry in the operating status data, the average specific resistance and filter cake prediction parameters of the current filtration process are determined, and the filtration stage of the filter press is determined based on the filtrate flow rate change curve in the operating status data. Based on the average specific resistance, the filter cake prediction parameters, and the filtration stage of the filter press, a control command sequence for the filter press is generated; Based on the control command sequence, the operation of the filter press is controlled, and the parameter deviation between the actual operating parameters of the filter press and the preset operating parameters in the control command sequence is determined. In response to the parameter deviation being less than a preset deviation threshold, the filter press is determined to be in a slight deviation state. Self-healing control is then performed on the filter press to adjust the actual operating parameters of the filter press to within the allowable tolerance range of the preset operating parameters, thereby maintaining the normal operation of the filter press.

[0006] Secondly, embodiments of this application also provide an intelligent control and operation system for a filter press, the system comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform an intelligent control and operation method for a filter press as described above.

[0007] Thirdly, embodiments of this application also provide a computer storage medium storing computer-executable instructions, which, when executed, implement an intelligent control operation method for the entire filter press as described above.

[0008] The intelligent control operation method and system for a filter press provided in this application embodiment have the following beneficial effects: First, acquiring operational status data during the filter press's operation provides a comprehensive understanding for subsequent decision-making, ensuring the real-time nature and accuracy of the data. Next, based on the real-time viscosity and concentration of the feed slurry in the operational status data, the average specific resistance and predicted filter cake parameters for the current filtration process are determined. Furthermore, based on the filtrate flow rate change curve in the operational status data, the filtration stage of the filter press is determined. By utilizing real-time viscosity and concentration in conjunction with the filtrate flow rate change, the limitations of traditional methods that only monitor pressure and time can be overcome. This allows for the accurate derivation of the average specific resistance and predicted filter cake parameters for the current filtration process, and the determination of the filter press's filtration stage. This provides insight into the internal physical state of the filter press, thereby resolving process mismatch issues caused by "black box" operation. Subsequently, based on the average specific resistance, predicted filter cake parameters, and the filter press... In the filtration stage, a dynamic sequence of control commands for the filter press is generated, replacing rigid fixed parameters. This allows for adaptive matching of the optimal pressing strategy based on material characteristics, ensuring filter cake quality while significantly reducing energy consumption. Subsequently, the filter press is controlled according to the command sequence, while simultaneously monitoring the deviation between the actual operating parameters and the preset parameters. This forms a sensitive feedback loop, providing a basis for subsequent fault-tolerant control. Finally, when the parameter deviation is less than a preset deviation threshold, the filter press is determined to be in a slightly deviated state, and self-healing control is implemented. By automatically adjusting the actual operating parameters, stable equipment operation is maintained without interrupting production, effectively preventing unplanned downtime due to minor faults and greatly improving overall equipment efficiency and operational reliability. Attached Figure Description

[0009] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating an intelligent control operation method for a filter press as provided in this application embodiment; Figure 2 This is a schematic diagram of the internal structure of an intelligent control system for a filter press, provided as an embodiment of this application. Detailed Implementation

[0010] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0011] It is understood that in the embodiments of this application, data related to user information (such as user accounts) is involved. When the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with relevant laws, regulations and standards.

[0012] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0013] In the following description, the terms “first, second, ...” are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that “first, second, ...” may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0014] Filter presses, as a mature solid-liquid separation device, are widely used in mining, chemical, and environmental protection fields. In related technologies, filter press control systems are mostly based on PLCs, typically using preset time-pressure curves for control. However, due to fluctuations in the viscosity, concentration, and other physical properties of the feed slurry, fixed control curves often cannot adapt to actual working conditions, leading to unstable filter cake moisture content, excessive energy consumption, or filter cloth clogging.

[0015] To monitor the actual operating conditions of filter presses in real time, digital twin technology has been introduced. However, this technology mainly focuses on 3D visualization and offline simulation. The digital twin model serves only as a data display window and does not deeply participate in real-time control decisions. Furthermore, the technology lacks effective online inversion methods for key physical parameters inside the filter press, making it difficult to dynamically adjust the pressing strategy based on the actual formation state of the filter cake. In addition, during the pressing process, slight deviations often occur due to factors such as residue inclusions on the filter plate sealing surface. The technology typically issues direct warnings and shutdowns for such faults, resulting in unqualified moisture content in the current batch of filter cake or unplanned shutdowns, severely impacting the overall efficiency of the equipment.

[0016] Based on this, the embodiments of this application provide an intelligent control operation method for the entire filter press, which can effectively solve the problems of unstable filter cake parameters and unplanned shutdowns caused by fixed parameters in traditional filter presses, thereby significantly improving the reliability and intelligence level of equipment operation.

[0017] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0018] Figure 1This is a flowchart illustrating an intelligent control operation method for a filter press as provided in an embodiment of this application. This method can be applied to intelligent control scenarios for filter presses in various settings. For example, in the dewatering of fine tailings in a mineral processing plant, the feed slurry has high viscosity and high specific resistance. After acquiring high viscosity data in real time using this application, the digital twin model calculates the high specific resistance and thick filter cake morphology, and then generates a stepped pressure-pressing curve to avoid instantaneous high pressure causing filter cake cracking or material spraying. If a slight deviation occurs due to slag inclusions on the filter plate sealing surface during execution, the system can automatically adjust the pressure set by the hydraulic station overflow valve for pressure compensation to maintain high pressure without interrupting the feed, ensuring thorough dewatering of high-viscosity tailings. In the dewatering of raw coal slime in a coal washing plant, considering the fine particle size and easy caking of coal slime, this application can determine that the filter cake is in the late stage of constant pressure filtration and the filter cake thickness is appropriate based on real-time concentration and flow rate change rate, and generate a command sequence of constant high pressure combined with pulse pressure holding. This ensures that the moisture content meets the standard while avoiding long-term full-load operation of the hydraulic system. If a slight deviation in pressure is detected during execution, the system starts a backup pressure-replenishing pump for brief pressure replenishment. After the batch is unloaded, an automatic filter cloth cleaning warning is triggered, balancing energy efficiency and equipment health. In the dewatering of fine chemical sludge in the chemical industry, given the complex composition and easy clogging of filter cloths by chemical sludge, this application focuses on monitoring the change rate of filtrate flow to determine the switching point of the filtration stage. When an abnormal increase in specific resistance is calculated, the pressure holding time is automatically shortened and the number of air blowers is increased to prevent excessive clogging of the filter cloth. If a slight deviation occurs, the clamping force of the clamping cylinder is finely adjusted to prevent the expensive filter plate from breaking due to a sudden increase in pressure, achieving precise fault tolerance. In the dewatering of residual activated sludge in municipal wastewater treatment plants, the sludge has a high organic matter content, low specific resistance, and strong hydrophilicity. After identifying a low specific resistance value, this application generates a high-frequency pulse pressure holding command. By intermittently applying pressure to squeeze out capillary water, ineffective energy consumption is significantly reduced. If a slight deviation causes a slow drop in pressure, the system can automatically increase the pressure holding frequency and extend the single pressure holding cycle. By dynamically correcting the control parameters, operation is maintained until the end of the batch before equipment maintenance, effectively balancing energy efficiency and equipment health.

[0019] This application provides an intelligent control operation method for a filter press. It should be noted that the execution entity in this embodiment can be a server or any terminal device with data processing capabilities. For example, the server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The terminal device can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, vehicle terminal, etc., but is not limited to these.

[0020] like Figure 1 As shown in the embodiment of this application, an intelligent control operation method for a filter press includes the following steps: Step 101: Obtain the operating status data of the filter press during operation.

[0021] It should be noted that the operating status data includes multiple dimensions of status data, such as physical field, physical property field, and process-derived data. Physical field data describes the external forces and environmental conditions of the filter press, such as pressure data, flow data, displacement data, electrical data, and environmental data. Physical property field data describes the physicochemical properties of the feed slurry itself, such as real-time viscosity, real-time concentration, and temperature data. Process-derived data are state quantities calculated based on physical field data or physical property field data, such as filtrate flow rate change rate, pressure deviation, and filter cake thickness. Different devices can be used to collect different operating status data. For example, pressure data can be collected using a high-precision pressure transmitter, flow data can be collected using an electromagnetic flowmeter or vortex flowmeter, displacement data can be collected using a draw-wire displacement sensor or linear grating ruler, real-time viscosity data can be collected using an online viscometer, and real-time concentration data can be collected using an online concentration meter, etc. No specific limitations are made here.

[0022] As an example, taking the dewatering scenario of residual activated sludge in a municipal wastewater treatment plant, high-precision sensors are installed at key nodes of the filter press system. Specifically, an electromagnetic flowmeter (measuring flow rate Q) and a pressure transmitter (measuring feed pressure P) are installed on the feed pipe; a rope displacement sensor (measuring plate displacement S) is installed on the main hydraulic cylinder; a turbidity meter (to assist in determining the dewatering endpoint) is installed at the filtrate outlet; and an online viscometer and online concentration meter are installed on the sludge feed pump outlet pipe. Subsequently, the data acquired by these sensors is transmitted in real-time to the field PLC and edge computing gateway via an industrial bus. Afterward, the collected data undergoes data cleaning. For example, if the viscometer reading suddenly jumps (e.g., due to air bubbles passing through), the system automatically removes the outlier and takes the average of the previous 10 cycles as the current viscosity. Finally, the system packages the cleaned data into a data package containing all dimensions of the operating status (corresponding to the operating status data during the filter press operation) and sends it to the digital twin model. For example, the real-time viscosity in the operating status data package... The real-time concentration is 4500 cP. It is 4.5%, and the feed pressure is 4.5%. The instantaneous filtrate flow rate is 0.8 MPa. The pressure plate displacement is 120 L / min. For 350mm, the flow rate change rate The value is -5 L / (min·s).

[0023] Step 102: Based on the real-time viscosity and real-time concentration of the feed slurry in the operating status data, determine the average specific resistance and filter cake prediction parameters of the current filtration process.

[0024] It should be noted that the average specific resistance of the current filtration process is a physical parameter that measures the permeability of the filter cake. It is used to characterize the resistance encountered by the fluid when flowing through the filter cake per unit filtration area and per unit filter cake thickness. Filter cake prediction parameters may include relevant parameters of the filter cake such as filter cake thickness, filter cake moisture content, and filter cake washing rate.

[0025] In some embodiments, step 102 described above can be implemented as follows: using a digital twin model, based on the real-time concentration of the feed slurry and a preset solid particle density constant, the dry solids mass coefficient corresponding to a unit filtrate is determined; based on the filtration equation, the real-time viscosity of the feed slurry, the dry solids mass coefficient, and the filtration pressure difference in the operating status data are back-calculated in real time to obtain the average specific resistance value of the current filtration process; using a filter cake filling rate model, based on the average specific resistance value, the dry solids mass coefficient, the filtrate volume in the operating status data, and a preset filtration area, the current filter cake is estimated in real time to obtain the filter cake prediction parameters of the current filter cake.

[0026] Thus, by using real-time concentration and solid density to determine the dry solids mass coefficient, measurement errors caused by material composition fluctuations can be eliminated, laying a physical foundation for subsequent calculations. Furthermore, by using the filtration equation to calculate the average specific resistance in real time, the limitations of traditional sensors that can only monitor external pressure can be overcome, allowing direct insight into the permeation resistance characteristics inside the filter cake. Moreover, by combining the specific resistance and filter cake filling rate model to dynamically estimate filter cake parameters, replacing the indirect measurement of traditional displacement sensors or fixed empirical values, it is possible not only to monitor the filling status of the filter chamber in real time, but also to provide a reliable decision-making basis for subsequent adaptive generation of intelligent commands such as stepped pressure increase or pulse pressure maintenance through dual verification of the average specific resistance and filter cake parameters. This effectively prevents filter cake cracking, excessive moisture content, or energy waste at the source.

[0027] It should be noted that the solid particle density constant refers to the true density of the solid particles that make up the filter cake skeleton; the dry solids mass coefficient refers to the mass of dry solids that needs to be retained to produce a unit volume of filtrate, and is used to characterize the degree of material concentration; the filtration pressure difference refers to the pressure difference between the two sides of the filter cake; and the filter cake filling rate model is a mathematical model used to describe the percentage of the pore volume inside the filter cake to the total volume.

[0028] As an example, taking the dewatering scenario of excess activated sludge from a municipal wastewater treatment plant as an example, assuming the solid particle density of the municipal sludge is... The filter cake prediction parameter is the filter cake thickness, and the real-time concentration of the current feed slurry is obtained from the operating status data. The digital twin model then uses the input solid particle density... and real-time concentration The dry solids mass coefficient is calculated using formula (1). Subsequently, the filter pressure difference in the operating status data is obtained as follows: The current real-time viscosity of the slurry is Filtering time is The cumulative filtrate volume is The filter cloth pressure is Filter area is The digital twin model dynamically fits the Ruth filtering equation (Equation (2)) and performs real-time back-calculation to obtain the average specific resistance of the current filtering process. Subsequently, the model utilizes the filter cake porosity from the filter cake porosity model. Based on the average specific resistance Dry solids mass coefficient Cumulative filtrate volume Filter area The thickness of the current filter cake is calculated using formula (3). .

[0029] (1) (2) (3) In some embodiments, after performing step 102 above, the following processing may also be performed: obtaining the actual moisture content of the current filter cake; predicting the moisture content of the current filter cake based on the average resistivity using the digital twin model to obtain the target moisture content of the current filter cake; determining the moisture content deviation between the target moisture content of the current filter cake and the actual moisture content of the current filter cake; and correcting the filter cloth resistance parameter and filter cake porosity parameter of the digital twin model based on the moisture content deviation in response to the moisture content deviation being greater than a preset deviation range to obtain a corrected digital twin model.

[0030] In this way, by comparing the actual measured moisture content with the target moisture content predicted by the model based on the current specific resistance, the model prediction error can be accurately detected. When the moisture content deviation is detected to exceed the preset range, the filter cloth resistance parameter and filter cake porosity parameter in the digital twin model can be corrected in reverse. This ensures that the control commands for subsequent batches are always generated based on the accurate physical model, avoiding energy waste or product quality degradation caused by model distortion. Furthermore, it can achieve self-maintaining control accuracy throughout the entire life cycle of the filter press, greatly reducing operation and maintenance costs and improving the intelligence level of filter press control.

[0031] It should be noted that the filter cloth resistance parameter refers to the resistance of the filter cloth itself to fluid flow; the filter cake porosity refers to the percentage of the pore volume inside the filter cake to the total volume.

[0032] As an example, taking the dewatering scenario of residual activated sludge in a municipal wastewater treatment plant, after the current batch of filter cake is dewatered, the actual moisture content of the filter cake is 78%. The digital twin model, based on the average specific resistance and process data during the operation of this batch, uses a built-in prediction algorithm to calculate the theoretical target moisture content of 73% under the current pressing strategy. By calculating the difference between the two, the moisture content deviation is found to be 5%, which is greater than the preset deviation range of ±2%. Subsequently, a parameter correction strategy is initiated for the digital twin model, increasing the filter cloth resistance parameter by 15% and simultaneously decreasing the filter cake porosity parameter by 5%, thus obtaining a corrected digital twin model. The corrected digital twin model can automatically generate a more reasonable pressing curve based on the updated filter cloth resistance and filter cake porosity parameters when the next batch of sludge enters, thereby ensuring that the moisture content of the final filter cake returns to the standard.

[0033] Step 103: Based on the filtrate flow rate change curve in the operating status data, determine the filtration stage of the filter press.

[0034] It should be noted that the filtration stage refers to a period of time with clear physical meaning that is divided within a working cycle of the filter press according to the different filtration resistance states exhibited by the change rate of filtrate flow. In this application, the working process of the filter press can be divided into a constant speed filtration stage, a transition stage, a constant pressure filtration stage, and a compaction stage.

[0035] In some embodiments, step 103 described above can be implemented as follows: In response to the filtrate flow rate change rate at a first moment in the filtrate flow rate change rate curve being greater than or equal to a first change rate threshold, the filtration stage of the filter press at the first moment is determined to be a constant-rate filtration stage; in response to the filtrate flow rate change rate at a first moment in the filtrate flow rate change rate curve being less than the first change rate threshold and the filtrate flow rate being greater than a second change rate threshold, the filtration stage of the filter press at the first moment is determined to be a transition stage, the filtration stage of the transition stage being consistent with the most recent filtration stage of the filter press; in response to the filtrate flow rate change rate at a first moment in the filtrate flow rate change rate curve being less than or equal to the second change rate threshold, the filtration stage of the filter press at the first moment is determined to be a constant-pressure filtration stage; in response to the current filtrate flow rate at the first moment in the operating status data being less than a minimum flow rate threshold, the filtration stage of the filter press at the first moment is determined to be a compaction stage.

[0036] Thus, dividing the filtration process into four physical states—constant speed, transition, constant pressure, and compaction—using the rate of change threshold better aligns with the fluid dynamics of filter cake growth. Furthermore, by setting a transition phase, the frequent shifts in control strategies caused by instantaneous flow fluctuations can be effectively mitigated, ensuring system stability. This division also allows the digital twin model to calculate the average resistivity and filter thickness within the correct physical context, ensuring that pressure is not blindly increased during the constant speed phase and energy consumption is not excessive during the constant pressure phase. This provides a reliable timing basis for generating a dynamic pressing strategy based on the average resistivity, significantly improving the robustness of the overall machine control and process consistency.

[0037] It should be noted that the first moment is used to describe any moment in the filtrate flow rate change curve; the constant-rate filtration stage refers to the initial filtration period when the filter cake has not yet formed or is extremely thin, at which time the filtration resistance mainly comes from the filter cloth; the transition stage refers to the period when the filter cake begins to thicken significantly, the resistance gradually increases, and the filtrate flow rate begins to decrease rapidly, but has not yet reached the level requiring full-power pressing; the constant-pressure filtration stage refers to the period when the filter cake has formed a certain thickness, and the filter cake becomes the main filtration resistance. At this time, it is difficult to push the liquid through by the feed pump alone, and external pressing pressure must be applied to maintain the flow rate; the compaction stage refers to the period when the filter cake has basically stopped producing water, the filtration process is over, and the system maintains high pressure to further densify the filter cake and reduce its moisture content through mechanical extrusion.

[0038] As an example, taking the dewatering scenario of residual activated sludge in a municipal wastewater treatment plant as an example, the system collects filtrate flow meter data in real time to obtain the filtrate flow rate change curve. Assuming that the filtrate flow rate change at time i is greater than or equal to the first change rate threshold (e.g., -2 L / min²), the system determines that time i is the constant rate filtration stage; when the filtrate flow rate change at time i is less than the first threshold (e.g., -2 L / min²) but greater than the second threshold (e.g., -10 L / min²), the system determines that time i is the transition stage; when the filtrate flow rate change at time i is less than or equal to the second change rate threshold (e.g., -10 L / min²), the system determines that time i is the constant pressure filtration stage; when the system detects that the current filtrate flow rate at time i is less than the minimum flow rate threshold (e.g., 5 L / min), it indicates that the filter cake has basically stopped effluent, and the system determines that time i is the compaction stage.

[0039] Step 104: Based on the average specific resistance, the filter cake prediction parameters, and the filtration stage of the filter press, generate the control command sequence for the filter press.

[0040] It should be noted that the control command sequence refers to the structured instruction set output by the digital twin model, which includes time sequence, pressure setting, valve action, etc., used to directly drive physical equipment to perform corresponding actions.

[0041] In some embodiments, step 104 described above can be implemented as follows: Based on the average specific resistivity, determine the initial pressing strategy of the filter press; in response to the filter press's filtration stage being a constant-rate filtration stage, determine the final pressing strategy of the filter press as closing the pressing valve and maintaining the feed pump at full frequency; in response to the filter press's filtration stage being a constant-pressure filtration stage or a compaction stage, use the initial pressing strategy as the final pressing strategy of the filter press; map the filter cake prediction parameters to obtain a duration correction coefficient, and based on the duration correction coefficient, correct the basic holding time to obtain the final holding time; combine the final pressing strategy and the final holding time to obtain the control command sequence of the filter press.

[0042] In this way, by using the average specific resistance to precisely match the initial pressing strategy, it is possible to ensure that no material spraying or cracking occurs when dealing with difficult materials, and no energy waste occurs when dealing with easy-to-filter materials. At the same time, dynamic decision-making is combined with the filtration stage. During the constant-rate filtration stage, the pressing valve is resolutely closed to maintain the feeding efficiency, and the pressing is fully executed during the constant-pressure filtration stage. This can achieve seamless connection of process logic. Furthermore, by introducing filter cake prediction parameters to flexibly adjust the holding time, it is possible to minimize the ineffective holding time while ensuring that the moisture content meets the standard, thereby significantly improving the overall processing capacity and energy efficiency ratio of the machine.

[0043] It should be noted that the duration correction coefficient is a dimensionless proportional coefficient dynamically calculated based on real-time filter cake prediction parameters (such as filter cake thickness). It is used to measure the current filter cake prediction parameters and convert them into adjustment weights for time parameters. The holding time refers to the length of time after the pressing stage ends when the filter press maintains the highest working pressure without unloading, so as to use continuous static pressure to force the capillary water and bound water inside the filter cake to be further discharged.

[0044] As an example, taking the dewatering of excess activated sludge from a municipal wastewater treatment plant, assuming the filter cake prediction parameter is the filter cake thickness, the digital twin model determines the average specific resistivity of the filter cake to be 1.2 × 10⁻⁶ based on the real-time viscosity and concentration data from the operating status. 12 The system calculates the filter cake thickness (m / kg) and matches the average resistivity to determine the initial pressing strategy (e.g., stepped pressure increase). If the system identifies the current filtration stage as a constant-rate filtration stage, it rejects the initial pressing strategy based on the matched values ​​and adjusts the final pressing strategy to "close the pressing valve and maintain full-frequency operation of the feed pump." If the system identifies the filtration stage as a constant-pressure filtration stage or a compaction stage, it uses the initial pressing strategy as the final pressing strategy. Simultaneously, the current filter cake thickness is calculated. The filter cake prediction parameter is 35mm, based on the mapping function (e.g., The duration correction coefficient is obtained through mapping processing. Meanwhile, based on the duration correction factor For basic pressure holding time After making adjustments, the final pressure holding time can be obtained. for Finally, the final pressing strategy and final holding time will be determined. The commands are combined and packaged to obtain a sequence of control instructions for controlling the operation of the filter press.

[0045] In some embodiments, the above-described determination of the initial pressing strategy of the filter press based on the average specific resistivity can be achieved in the following ways: in response to the average specific resistivity being greater than or equal to a first specific resistivity threshold, the initial pressing strategy of the filter press is determined to be a stepped pressure increase; in response to the average specific resistivity being greater than a second specific resistivity threshold and the average specific resistivity being less than the first specific resistivity threshold, the initial pressing strategy of the filter press is determined to be a constant high pressure; in response to the average specific resistivity being less than or equal to the second specific resistivity threshold, the initial pressing strategy of the filter press is determined to be a pulse pressure holding.

[0046] Thus, for high resistivity materials, a stepped pressurization strategy is adopted, using low-pressure pre-compression to build a stable filter cake skeleton before gradually increasing to high pressure, which can effectively avoid filter cake penetration or sealing surface damage caused by instantaneous high pressure. For medium resistivity materials, a constant high pressure strategy can be directly adopted, which simplifies the control logic while ensuring dewatering efficiency. For low resistivity easily filtered materials, a pulse pressure holding strategy is adopted, using intermittent pressure application instead of continuous high pressure, which can prevent excessive clogging of the filter cloth and significantly reduce the ineffective energy consumption and heat generation of the hydraulic system. Furthermore, through an adaptive decision-making mechanism, the operation control of the filter press can be unaffected by fluctuations in the properties of the feed material, ensuring that the filter press always operates at the optimal operating point, thereby significantly improving the equipment's adaptability to different materials and its overall energy efficiency.

[0047] It should be noted that step-by-step pressure increase refers to a pressing control strategy that increases the pressing pressure to the maximum value in stages and steps; constant high pressure refers to a pressing control strategy that instantly increases the pressure to the set maximum working pressure and maintains that pressure value until the end of the holding pressure period; pulse holding pressure refers to a pressing control strategy in which the pressure is not constant during the holding pressure period, but fluctuates periodically between high and low pressure.

[0048] As an example, taking the tailings dewatering scenario in a mine beneficiation plant as an example, assuming the material being processed is fine mud tailings, the system uses a digital twin model to perform real-time back-calculation to obtain an average specific resistivity of 1.5 × 10⁻⁶. 12 m / kg, greater than the system's preset first specific resistance threshold of 1.0 × 10 12 Based on the m / kg, the initial pressing strategy is determined to be a stepped pressurization approach: first, pre-press at 0.8 MPa for 60 seconds to build the filter cake framework; then, increase to 1.2 MPa for 120 seconds; and finally, maintain high pressure at 1.6 MPa to prevent filter cake cracking or material ejection caused by instantaneous high pressure. Assuming the material being processed is medium-grained tailings, the system uses a digital twin model to perform real-time back-calculation, obtaining an average specific resistivity of 6.0 × 10⁻⁶. 11 m / kg, less than the system's preset first specific resistance threshold of 1.0 × 10 12 m / kg and greater than the system's preset second specific resistance threshold of 4.0 × 10 11 If the pressure is m / kg, then the initial pressing strategy is determined to be constant high pressure. This means the system instructs the hydraulic station to directly output 1.6 MPa full pressure and maintain this pressure for 300 seconds to complete dewatering as quickly as possible and improve processing efficiency. Assuming the material being processed is coarse-grained tailings, the system uses a digital twin model to perform real-time back-calculation, obtaining an average specific resistivity of 2.0 × 10⁻⁶. 11 m / kg, which is less than the system's preset second specific resistance threshold of 4.0 × 10⁻⁶. 11If the pressure is m / kg, then the initial pressing strategy is determined to be pulse pressure holding. That is, the system first quickly rises to a high pressure of 1.6MPa, maintains it for 10 seconds, and then quickly depressurizes it to 0.5MPa and maintains it for 5 seconds. This cycle is repeated to prevent coarse particles from clogging the filter cloth pores and to avoid over-pressurization of easily filterable materials, thereby significantly reducing energy consumption.

[0049] Step 105: Based on the control command sequence, control the operation of the filter press and determine the parameter deviation between the actual operating parameters of the filter press and the preset operating parameters in the control command sequence.

[0050] It should be noted that the actual operating parameters of a filter press may include parameters such as pressure, flow rate, and pressing pressure, which are not specifically limited here.

[0051] As an example, taking the dewatering scenario of fine mud tailings in a mining beneficiation plant as an example, the actual operating parameter of the press is the pressing pressure. The system generates a control command sequence according to the aforementioned steps (for example, the first stage is low pressure of 0.8MPa for 60 seconds, the second stage is medium pressure of 1.2MPa for 120 seconds, and the third stage is high pressure of 1.6MPa for 300 seconds). Then, the system executes operation control on the filter press according to the control command sequence. Assuming that during the first stage of low pressure holding, the PLC drives the hydraulic station to output pressure, and the digital twin model collects the actual pressing pressure (corresponding to the actual operating parameter) in real time through the pressure transmitter installed on the main oil cylinder, which is 0.79MPa, and the preset pressure (preset operating parameter) in the control command sequence is 0.8MPa, then the pressure deviation (parameter deviation) can be calculated to be 0.01MPa.

[0052] Step 106: In response to the parameter deviation being less than a preset deviation threshold, it is determined that the filter press is in a slight deviation state. Self-healing control is then performed on the filter press to adjust the actual operating parameters of the filter press to within the allowable tolerance range of the preset operating parameters, thereby maintaining the normal operation of the filter press.

[0053] It should be noted that the micro-deviation state refers to the abnormal operating condition in which the actual pressing pressure slowly decreases during the pressure holding stage of the filter press, but the rate and magnitude of the decrease have not yet reached the shutdown standard; self-healing control refers to the intelligent control strategy that, after the system detects a micro-deviation, does not interrupt the current production batch, but instead compensates for the pressure loss caused by leakage by automatically adjusting the actuator parameters (such as increasing the hydraulic pump output, increasing the clamping force, etc.), so that the system recovers and maintains within the target pressure range.

[0054] As an example, taking the dewatering scenario of residual activated sludge in a municipal wastewater treatment plant, when the filter press enters the high-pressure holding stage, the system command preset pressure (command preset operating parameter) is 1.6MPa. However, the digital twin model monitors that the actual pressure (actual operating parameter) of the main oil cylinder is only 1.52MPa, and it shows a slow downward trend. The system calculates that the pressure deviation is 0.08MPa, which is less than the preset deviation threshold (e.g., 0.1MPa). It is determined that the filter press is in a slightly deviated state. The system immediately starts self-healing control to bring the actual pressing pressure of the filter press back to the allowable error range of the command preset pressure (e.g., ±0.05MPa) to ensure that the filter press can continue to complete the remaining holding time and ensure that the current batch of sludge can be completely dried without interrupting the current production batch. This achieves the self-repair and continuous stable operation of the equipment without interrupting production.

[0055] In some embodiments, the self-healing control of the filter press in step 106 above can be achieved by: automatically increasing the feed pressure and flow rate of the filter press, or starting a backup pump to compensate for the actual operating parameters of the filter press; reducing the health of the filter press, and triggering a maintenance warning in response to the health being less than a preset health threshold.

[0056] Thus, when a slight deviation is detected, the system first compensates for the actual operating parameters of the filter press by increasing the feed pressure and flow rate or starting the backup pump. This ensures that the current batch is not interrupted due to slight deviations, maintaining the continuity of production and the stability of the filter cake quality. Furthermore, the system reduces the equipment health status according to the frequency of deviations or the cumulative compensation amount. When the health status falls below the preset threshold, the system triggers a maintenance warning, which can prevent the accumulation of hidden faults from causing sudden shutdowns or filter plate bursts. It also provides maintenance personnel with a window for planned maintenance, thereby achieving the best balance between short-term fault tolerance and long-term reliability, significantly reducing the rate of unplanned downtime and extending the service life of key components.

[0057] As an example, taking the dewatering scenario of residual activated sludge in a municipal wastewater treatment plant, the actual operating parameter is the actual pressing pressure. During the high-pressure holding stage, the system monitored that the actual pressing pressure (actual operating parameter) dropped from the preset command pressure (preset command operating parameter) of 1.6 MPa to 1.52 MPa, with a pressure deviation (parameter deviation) of 0.08 MPa (less than the preset deviation threshold of 0.1 MPa), indicating that the filter press was currently in a slightly deviated state. Subsequently, the system immediately implemented self-healing control, automatically increasing the feed pressure from 1.6 MPa to 1.72 MPa and starting the standby pump to intermittently replenish oil to the main oil cylinder. The output force of the pressing cylinder increased accordingly, causing the actual pressing pressure to quickly recover and stabilize at 1.59 MPa. Within the allowable tolerance range of 1.61 MPa, the system allows the current batch of sludge to continue pressure dewatering without shutting down. Simultaneously, the system deducts points from the current filter press's health status (e.g., an initial maximum of 100 points, with 5 points deducted for each minor deviation). Assuming this is the third minor deviation, the health status has dropped from 90 to 85 points. If subsequent minor deviations occur frequently due to filter cloth aging or sealing surface wear, causing the health status to continuously decline to 60 points (the preset health threshold), the system determines that the equipment has a potential failure trend and triggers a maintenance warning. A prompt will appear on the operation interface suggesting a shutdown to check the filter cloth and clean the filter plate sealing surface, and a maintenance work order will be generated. However, an emergency stop is not forced; planned maintenance will be arranged after the current batch is unloaded.

[0058] In some embodiments, after performing step 106 above, the following processing may also be performed: in response to the parameter deviation being greater than or equal to the preset deviation threshold, a maintenance warning is triggered, and the filter press is shut down for maintenance.

[0059] Thus, when the parameter deviation is greater than or equal to the preset deviation threshold, it indicates that the fault has exceeded the self-compensation capability. Continuing to operate will not only fail to guarantee the moisture content of the filter cake, but may also cause equipment damage or personal safety accidents. By forcibly triggering the maintenance warning and shutting down for maintenance, the fault can be prevented from escalating.

[0060] As an example, taking the dewatering scenario of residual activated sludge in a municipal wastewater treatment plant, when the filter press enters the high-pressure holding stage, the system issues a preset pressure (preset operating parameter) of 1.6 MPa. However, the actual pressing pressure (actual operating parameter) collected by the digital twin model through the main cylinder pressure transmitter is only 1.2 MPa, and the calculated pressure deviation (parameter deviation) is 0.4 MPa. By comparison, it can be seen that the pressure deviation is significantly greater than the preset deviation threshold (0.1 MPa). At this time, the system immediately triggers a maintenance warning. For example, a red alarm pops up on the host computer in the central control room: "Filter press pressure holding has seriously failed. Please stop the machine immediately for inspection!", and simultaneously sends a fault code (e.g., Err). E207: Abnormal drop in holding pressure) and the time of occurrence are logged, and staff are notified via SMS / audio-visual alarm. At the same time, the filter press is shut down for maintenance, such as automatically cutting off the feed pump and pressing valve, unloading the hydraulic station, and locking the filter press into a "maintenance lockout" state, preventing it from automatically entering the next work cycle. It can only be put back into operation after on-site inspection and maintenance (such as replacing damaged filter plates, tightening hydraulic joints, and replacing seals) and manual reset of the fault, to ensure the safe operation of the equipment.

[0061] In some embodiments, after performing step 106 above, the following processing may also be performed: obtain the actual parameters of the current filter cake, and perform a pass rate analysis on the actual parameters of the current filter cake to obtain a pass rate analysis result; in response to the pass rate analysis result indicating that the current filter cake has a high moisture content, trigger secondary pressing and blowing to reduce the moisture content of the current filter cake.

[0062] Thus, by monitoring the actual parameters of the current filter cake and identifying when the filter cake moisture content is high through pass rate analysis, the system triggers secondary pressing and blowing. Compressed air is used to back-blown the filter cake to separate it from the filter cloth and further remove capillary water, thereby reducing the filter cake moisture content and reducing manual workload. By integrating "physical sensing + visual perception" into closed-loop control, the side effects of high-pressure strategies under extreme materials can be prevented, and proactive process remedial measures can be provided for the problem of sticking to the plate, thereby significantly improving the unloading success rate, filter cloth regeneration quality, and the dewatering effect of the final product.

[0063] It should be noted that the above-mentioned pass rate analysis method can be achieved through threshold comparison or through predictive analysis using a trained model; no specific limitations are made here.

[0064] As an example, taking the dewatering scenario of residual activated sludge in a municipal wastewater treatment plant as an example, before the filter press unloads, the average moisture content (actual parameter) of the filter cake is measured to be 50% by a sensor. Subsequently, the system compares the actual parameter of the filter cake with the preset parameter threshold, that is, it performs a pass rate analysis. When the actual parameter (moisture content 50%) is detected to be greater than the preset parameter threshold (moisture content 40%), the pass rate analysis result is that the current filter cake moisture content is high. At this time, a secondary pressing and blowing will be triggered. That is, the pressing pump is first controlled to perform secondary pressing at medium pressure (e.g., 0.6 MPa) for 120 seconds. Then the blower is started to blow hot air (e.g., 80℃) into the filter cake through the air blowing channel in the center of the filter plate for 180 seconds to reduce the moisture content of the filter cake.

[0065] In some embodiments, after performing step 106, the following processes may also be performed: obtaining the actual parameters of the filter cake before washing; mapping the actual parameters of the filter cake to obtain the amount of filter cake washing liquid, and generating a filter cake washing strategy based on the actual parameters of the filter cake and the amount of filter cake washing liquid; washing the filter cake based on the filter cake washing strategy, and monitoring the real-time flow rate of the washing liquid and the real-time pressure change curve of the washing liquid; determining the flow rate deviation between the real-time flow rate of the washing liquid and the preset flow rate of the washing liquid in the filter cake washing strategy, and determining the pressure deviation between the real-time pressure change curve of the washing liquid and the preset pressure change curve of the filter cake washing strategy; adjusting the washing parameters of the current filter cake based on the flow rate deviation and the pressure deviation to ensure the washing effect of the current filter cake.

[0066] Thus, by acquiring the actual parameters of the filter cake before washing and mapping them to calculate the precise amount of washing liquid, a customized washing strategy can be generated. This can prevent resource waste and incomplete washing caused by excessive or insufficient washing liquid from the source, thereby significantly improving the utilization efficiency of resources such as water and chemicals. Secondly, by synchronously monitoring the real-time flow and pressure change curves of the washing liquid and dynamically comparing them with the preset model curves in the strategy, abnormalities in the washing process can be accurately identified, and deviations can be calculated in real time. Based on these deviations, the washing parameters can be dynamically adjusted online, enabling automatic compensation for unpredictable fluctuations in operating conditions. This ensures that the washing effect remains stable within the optimal target range, which can not only significantly improve the uniformity of washing and the consistency of product quality, but also reduce the labor intensity of operators. Furthermore, through refined control of the washing process, the environmental burden of subsequent treatment can be reduced, thereby achieving the unity of quality improvement, cost reduction, efficiency enhancement, and green production.

[0067] As an example, taking the filter press washing scenario of a mining company processing heavy metal slurry as an example, firstly, the system obtains the actual parameters of the filter cake through integrated sensors before washing. This includes the average thickness of the filter cake calculated based on the filter plate displacement at the end of pressing (e.g., 45 mm), the average concentration of target impurities (e.g., copper ions) in the filter cake measured by an online X-ray fluorescence analyzer (e.g., 1.2%), and the total dry weight of the filter cake obtained from the previous pressing cycle (e.g., 500 kg). Subsequently, the system maps the actual parameters of the filter cake and generates a washing strategy. The preset expert model calculates the theoretical washing liquid usage based on the filter cake thickness, impurity concentration, and dry weight by looking up a preset mapping table (or calculating empirical formulas). For example, if the model determines that the impurity concentration needs to be washed down to below 0.3%, a 5% dilute sulfuric acid solution needs to be used, with a total usage of approximately 1.5 times the filter cake weight, i.e., 750 kg of washing liquid. Based on this usage and the actual parameters, the system automatically generates a phased washing strategy. For example, the first phase uses a high flow rate (e.g., 20... The first stage involves displacement washing at a low flow rate (8 m³ / h) and a lower pressure (0.3 MPa) for 5 minutes; the second stage switches to a low flow rate (8 m³ / h) and a higher pressure (0.6 MPa). The system performs diffusion washing at a pressure of 0.6 MPa for 10 minutes, with pre-set theoretical flow rate and pressure change curves for each stage. Afterward, the system executes washing and monitors in real time. Upon initiation of the washing program, flow meters and pressure sensors monitor the real-time flow rate in the washing liquid pipeline and the real-time pressure between the filter plates, plotting the change curves. Simultaneously, during washing, the control unit compares the real-time flow rate with the pre-set flow rate for the current stage every second, calculating the flow deviation. It also compares the real-time pressure curve with the pre-set pressure curve in terms of shape, slope, and stability, calculating the overall pressure deviation. Finally, the system performs closed-loop adjustments. For example, two minutes after the start of the second stage of diffusion washing, if the system detects that the real-time pressure rise is significantly faster than the pre-set curve (excessive positive pressure deviation), indicating potential rapid blockage of the filter cake, the system dynamically adjusts the washing parameters based on the deviation value. It automatically reduces the feed pump frequency by 5%, slightly decreasing the actual flow rate, and temporarily adjusts the pre-set pressure limit for this stage from 0.6 MPa to 0.55 MPa. MPa; In this way, through this real-time feedback adjustment, the system can successfully avoid filter cake "compaction" and washing liquid short circuit caused by excessive pressure, ensuring that the washing liquid and impurities have sufficient contact time, thereby ensuring the final washing effect and making the filter cake concentration after washing stable to meet the design requirements.

[0068] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide an intelligent control and operation system for the entire filter press, the structure of which is as follows: Figure 2 As shown.

[0069] Figure 2This is a schematic diagram of the internal structure of an intelligent control system for a filter press, provided as an embodiment of this application. Figure 2 As shown, the system includes: At least one processor 201; And a memory 202 that is communicatively connected to at least one processor; The memory 202 stores instructions that can be executed by at least one processor. The instructions are executed by at least one processor 201 to enable at least one processor 201 to perform the steps of the method corresponding to any of the above embodiments.

[0070] Some embodiments of this application provide corresponding to Figure 1 A non-volatile computer storage medium stores computer-executable instructions configured to perform the steps of the method corresponding to any of the above embodiments.

[0071] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for IoT devices and media are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0072] The systems, media, and methods provided in this application are one-to-one correspondences. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0073] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0075] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0076] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0077] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0078] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0079] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0080] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0081] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for intelligent control and operation of a filter press, characterized in that, The method includes: Acquire the operating status data of the filter press during its operation; Based on the real-time viscosity and concentration of the feed slurry in the operating status data, the average specific resistance and filter cake prediction parameters of the current filtration process are determined, and the filtration stage of the filter press is determined based on the filtrate flow rate change curve in the operating status data. Based on the average specific resistance, the filter cake prediction parameters, and the filtration stage of the filter press, a control command sequence for the filter press is generated; Based on the control command sequence, the operation of the filter press is controlled, and the parameter deviation between the actual operating parameters of the filter press and the preset operating parameters in the control command sequence is determined. In response to the parameter deviation being less than a preset deviation threshold, the filter press is determined to be in a slight deviation state. Self-healing control is then performed on the filter press to adjust the actual operating parameters of the filter press to within the allowable tolerance range of the preset operating parameters, thereby maintaining the normal operation of the filter press.

2. The method according to claim 1, characterized in that, The determination of the average specific resistivity and filter cake prediction parameters of the current filtration process based on the real-time viscosity and concentration of the feed slurry in the operational status data includes: Using a digital twin model, the dry solids mass coefficient corresponding to a unit of filtrate is determined based on the real-time concentration of the feed slurry and the preset solid particle density constant. Based on the filtration equation, the real-time viscosity of the feed slurry, the dry solids mass coefficient, and the filtration pressure difference in the operating status data are back-calculated in real time to obtain the average specific resistance of the current filtration process. Using the filter cake filling rate model, based on the average specific resistance, the dry solids mass coefficient, the filtrate volume in the operating status data, and the preset filtration area, the current filter cake is estimated in real time to obtain the filter cake prediction parameters for the current filter cake.

3. The method according to claim 1, characterized in that, The determination of the filtration stage of the filter press based on the filtrate flow rate change curve in the operating status data includes: In response to the filtrate flow rate change rate being greater than or equal to a first change rate threshold at the first moment in the filtrate flow rate change rate curve, the filter press is determined to be in a constant-rate filtration stage at the first moment. In response to the fact that the filtrate flow rate change rate at a first moment in the filtrate flow rate change rate curve is less than the first change rate threshold and the filtrate change rate is greater than the second change rate threshold, the filtration stage of the filter press at the first moment is determined to be a transition stage, and the filtration stage of the transition stage is consistent with the most recent filtration stage of the filter press. In response to the fact that the rate of change of filtrate flow rate at the first moment in the filtrate flow rate change rate curve is less than or equal to the second rate of change threshold, the filter press is determined to be in a constant pressure filtration stage at the first moment. In response to the fact that the current filtrate flow rate at the first moment in the operating status data is less than the minimum flow rate threshold, the filter press is determined to be in the compaction stage at the first moment during the filtration stage.

4. The method according to claim 3, characterized in that, The step of generating a control command sequence for the filter press based on the average specific resistivity, the filter cake prediction parameters, and the filtration stage of the filter press includes: Based on the average specific resistivity, the initial pressing strategy of the filter press is determined; In response to the filter press's filtration stage being a constant-rate filtration stage, the final pressing strategy of the filter press is to close the pressing valve and maintain the feed pump running at full frequency. In response to whether the filtration stage of the filter press is a constant pressure filtration stage or a compaction stage, the initial pressing strategy is taken as the final pressing strategy of the filter press. The filter cake prediction parameters are mapped to obtain a duration correction coefficient, and the basic holding time is corrected based on the duration correction coefficient to obtain the final holding time. The final pressing strategy and the final holding time are combined to obtain the control command sequence of the filter press.

5. The method according to claim 4, characterized in that, The step of determining the initial pressing strategy of the press based on the average specific resistance value includes: In response to the average specific resistance being greater than or equal to a first specific resistance threshold, the initial pressing strategy of the filter press is determined to be a stepped pressurization. In response to the average specific resistance being greater than a second specific resistance threshold and the average specific resistance being less than a first specific resistance threshold, the initial pressing strategy of the filter press is determined to be constant high pressure. In response to the average specific resistance being less than or equal to the second specific resistance threshold, the initial pressing strategy of the filter press is determined to be pulse pressure holding.

6. The method according to claim 1, characterized in that, The self-healing control of the filter press includes: The feed pressure and flow rate of the filter press are automatically increased, or the standby pump is started to compensate for the actual operating parameters of the filter press; The health status of the filter press is reduced, and a maintenance warning is triggered in response to the health status falling below a preset health status threshold.

7. The method according to claim 1, characterized in that, The method further includes: In response to the parameter deviation being greater than or equal to the preset deviation threshold, a maintenance warning is triggered, and the filter press is shut down for maintenance.

8. The method according to claim 2, characterized in that, The method further includes: Obtain the actual moisture content of the current filter cake; Using the digital twin model, based on the average specific resistivity, the moisture content of the current filter cake is predicted to obtain the target moisture content of the current filter cake; Determine the moisture content deviation between the target moisture content of the current filter cake and the actual moisture content of the current filter cake; In response to the moisture content deviation being greater than a preset deviation range, the filter cloth resistance parameter and filter cake porosity parameter of the digital twin model are corrected based on the moisture content deviation to obtain the corrected digital twin model.

9. The method according to claim 1, characterized in that, The method further includes: Obtain the actual parameters of the filter cake before washing; The actual parameters of the filter cake are mapped to obtain the amount of filter cake washing liquid, and a filter cake washing strategy is generated based on the actual parameters of the filter cake and the amount of filter cake washing liquid. Based on the filter cake washing strategy, the filter cake is washed, and the real-time flow rate of the washing liquid and the real-time pressure change curve of the washing liquid are monitored. Determine the flow deviation between the real-time flow rate of the washing liquid and the preset flow rate of the washing liquid in the filter cake washing strategy, and determine the pressure deviation between the real-time pressure change curve of the washing liquid and the preset pressure change curve of the filter cake washing strategy; Based on the flow rate deviation and the pressure deviation, the washing parameters of the current filter cake are adjusted to ensure the washing effect of the current filter cake.

10. An intelligent control and operation system for a filter press, characterized in that, The system includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform an intelligent control operation method for a filter press as described in any one of claims 1-9.

Images