Intelligent monitoring method and system for landfill leachate zero discharge system

Abstract

The invention discloses an intelligent monitoring method and system for a landfill leachate zero discharge system, and particularly relates to the technical field of environmental protection equipment monitoring. According to the method, the working condition type is accurately recognized through the comprehensive similarity calculated by the Euclidean distance, the dynamic early warning threshold interval is constructed for different working conditions, false alarm or missing alarm caused by water inlet load fluctuation, environment temperature change and the like is avoided, the monitoring standard is accurately matched with the actual operation state, stable operation of the zero emission system is guaranteed, and the working efficiency is improved. And the working condition adaptability is obviously improved.

Description

Technical Field

[0001] This invention relates to the field of environmental protection equipment monitoring technology, and more specifically, to an intelligent monitoring method and system for zero-discharge systems for landfill leachate. Background Technology

[0002] Landfill leachate, a high-concentration organic wastewater generated during landfilling, incineration, and other waste treatment processes, is characterized by its complex composition, high pollutant concentration, and drastic fluctuations in water quality and quantity. Its harmless treatment is a key link in the resource recovery and harmless disposal of waste. Zero-discharge systems, through a combination of processes such as biochemical treatment, membrane separation, and evaporation crystallization, achieve deep removal of pollutants and crystallization and solidification of salts in leachate, and have become the most stringent and widely used leachate treatment technology.

[0003] However, existing monitoring methods and equipment for zero-emission systems still have some technical shortcomings, making them difficult to adapt to complex and ever-changing operating scenarios. Specific problems are as follows: Poor adaptability to operating conditions: Existing monitoring systems mostly use fixed threshold modes, which do not fully consider the impact of different operating conditions such as fluctuations in influent load, changes in ambient temperature, and adjustments to operating control parameters. This results in a mismatch between the threshold and the actual operating status, frequently triggering false alarms or missed alarms, which seriously affects the stable operation of the system. Insufficient accuracy of early warning: Early warning judgments rely heavily on the exceedance of a single process parameter, lack a comprehensive assessment of the core operating indicators of each process, and have not established an early warning mechanism that links process type with operating condition type. This makes it impossible to accurately identify potential risks such as sludge health deterioration, membrane fouling, and unstable crystallization process, resulting in a delayed early warning response. Insufficient data value mining: Historical health data, maintenance records, and alarm events accumulated during system operation have not been effectively integrated and utilized, making it impossible to optimize early warning standards through data learning, which makes it difficult to continuously improve the intelligence level of the monitoring system.

[0004] To address this, an intelligent monitoring method and system for zero-discharge landfill leachate systems have been developed. Summary of the Invention

[0005] To overcome the above-mentioned deficiencies of the prior art, embodiments of the present invention provide an intelligent monitoring method and system for a landfill leachate zero-discharge system.

[0006] To achieve the above objectives, the present invention provides the following technical solution: Intelligent monitoring methods for landfill leachate zero-discharge systems include: Step 1: Collect operating parameters of different process types in the landfill leachate zero-discharge system in real time and integrate them into a health dataset; Step 2: Collect in real time the influent load parameters, operation control parameters and environmental status parameters of the landfill leachate zero discharge system in the current time zone as a real-time operating condition set. Pre-construct reference operating condition sets corresponding to different operating condition types. Conduct a comprehensive evaluation of the real-time operating condition set in the current time zone and the reference operating condition sets of each operating condition type to determine the current operating condition type of the system. Step 3: Establish a historical database containing historical health datasets, maintenance records, and alarm events. Based on the historical database, use early warning learning logic to process the data and construct dynamic early warning threshold ranges for different process types under different operating conditions. Step 4: After classifying the real-time collected health dataset according to different process types, identify the type of operating condition and input it into the corresponding dynamic early warning threshold range for matching. If the match is successful, an early warning signal is triggered.

[0007] Specifically, the process type and operating parameters in step one include; Process types include biochemical treatment processes, membrane treatment processes, and crystallization treatment processes; Biochemical treatment process parameters include activated sludge health status index, nitrification efficiency deviation, and carbon-nitrogen ratio imbalance coefficient; Membrane treatment process parameters include fouling rate, desalination rate attenuation coefficient, and energy consumption ratio; The crystallization process parameters include the evaporator heating chamber temperature and the evaporator vacuum degree.

[0008] Specifically, step two involves determining the type of operating condition. The influent load parameters include influent flow rate, influent COD concentration, influent ammonia nitrogen concentration, and influent conductivity; Operating control parameters include membrane system recovery rate settings and evaporator feed concentration settings; The environmental condition parameter is the ambient temperature; The reference operating condition set includes influent load reference parameters, operation control reference parameters, and environmental condition reference parameters for the current operating condition type. Using Euclidean distance, the single-parameter similarity between the real-time working condition set and the reference working condition set is calculated. After weighted fusion, the comprehensive similarity between the real-time working condition set and each set of reference working conditions is calculated. The comprehensive similarity is compared with the set similarity threshold. Among the sets of comprehensive similarities below the threshold, the working condition type with the lowest comprehensive similarity is identified as the working condition type of the current coefficient.

[0009] Specifically, the logic for constructing the dynamic early warning threshold range in step three; Retrieve the case number of all alarm events from the historical database and integrate them into an alarm case set. Integrate cases other than alarm events into a reference case set. : Match relevant alarm cases to their respective process types within the alarm case set to form biochemical case sets, membrane case sets, and crystallization case sets; Historical health datasets within a set time zone prior to the alarm occurrence are extracted from relevant alarm cases of different process types and used as alarm datasets. The reference case set contains pre-marked cases for different process types under different operating conditions, serving as benchmark cases; For different process types, a comprehensive analysis is conducted by combining alarm datasets of all processes under the same operating conditions and corresponding benchmark cases to construct dynamic early warning threshold ranges for different process types under different operating conditions.

[0010] Specifically, The dynamic early warning threshold range corresponding to different operating conditions under biochemical treatment processes is constructed. The dynamic early warning threshold range corresponding to different operating conditions under biochemical treatment processes is constructed. From a collection of biochemical cases under different operating conditions, the sludge concentration, sludge settling ratio, dissolved oxygen, actual nitrification efficiency, influent COD concentration, and influent total nitrogen concentration of the set time zone before the alarm were extracted. The alarm concentration, alarm settling ratio, alarm dissolved oxygen, average nitrification efficiency, average COD concentration, and average total nitrogen concentration of each case were calculated by averaging. From the baseline cases in the reference case set, extract the normal concentration, normal sedimentation ratio, normal dissolved oxygen, reference efficiency, reference COD concentration, and reference total nitrogen concentration for the corresponding operating conditions. Sludge health status index: obtained by comprehensively processing alarm concentration, alarm settling ratio, alarm dissolved oxygen, normal concentration, normal settling ratio, and normal dissolved oxygen; Nitrification efficiency deviation: |Average nitrification efficiency - Reference efficiency| / Reference efficiency; Carbon-to-nitrogen ratio imbalance coefficient: |Actual carbon-to-nitrogen ratio - Reference carbon-to-nitrogen ratio| / Reference carbon-to-nitrogen ratio; where carbon-to-nitrogen ratio = COD concentration / total nitrogen concentration; The sludge health status index, nitrification efficiency deviation, and carbon-nitrogen ratio imbalance coefficient are comprehensively processed to output the biochemical early warning coefficient for each case under different working conditions. The biochemical warning coefficients of all cases under the same working condition are summarized, and the dynamic warning threshold range corresponding to the working condition is constructed by using its highest and lowest values ​​as boundaries.

[0011] Specifically, Dynamic early warning threshold ranges corresponding to different operating conditions under the membrane treatment process in China; From a collection of membrane case studies under different operating conditions, we extracted the transmembrane pressure difference, desalination rate, and energy consumption ratio for the set time zone before the alarm. Through formula Calculate the pollution rate; where and These represent the real-time transmembrane pressure difference at the end and beginning of the set time zone, respectively. Time zone duration; Using formula The desalination rate attenuation coefficient for each case under different operating conditions was calculated; where and These represent the desalination rates at the initial and final time points of the set time zone, respectively. From the baseline cases in the reference case set, the reference rate, reference attenuation coefficient, and reference energy consumption ratio for the corresponding operating conditions are extracted; and after comprehensive processing in combination with the fouling rate, desalination rate attenuation coefficient, and energy consumption ratio, the membrane warning coefficient for each case is obtained. The membrane early warning coefficients of all cases under the same working condition are summarized, and the dynamic early warning threshold range corresponding to the working condition is constructed by using its highest and lowest values ​​as boundaries.

[0012] Specifically, The dynamic early warning threshold range corresponding to different operating conditions under the membrane crystallization process is constructed in China; From the collection of crystallization cases under different operating conditions, the evaporator heating chamber temperature and evaporator vacuum degree of the set time zone before the alarm were extracted; the absolute value of the difference between the measured value and the set value at each time point was calculated, and then the temperature fluctuation value and vacuum degree fluctuation value were obtained by averaging. The reference temperature fluctuation and reference vacuum fluctuation under different operating conditions are extracted from the benchmark case. After comprehensive processing of the temperature fluctuation value and vacuum fluctuation value, the crystallization warning coefficient of each case under different operating conditions is output. The crystallization warning coefficients of all cases under the same working condition are summarized, and the dynamic warning threshold range corresponding to the working condition is constructed by using its highest and lowest values ​​as boundaries.

[0013] Specifically, the logic for triggering the warning signal in step four; After identifying the type of working condition, the alarm dataset is replaced with the current health dataset. The biochemical warning coefficient, membrane warning coefficient, and crystallization warning coefficient are calculated in combination with the corresponding benchmark case to form a real-time warning coefficient set. The set is then matched with the corresponding dynamic warning threshold range. If any coefficient in the real-time warning coefficient set is within the corresponding dynamic warning threshold range, the warning signal of the corresponding coefficient is triggered.

[0014] Specifically, triggering an early warning signal automatically retrieves case records of handling similar operating conditions from the historical database; The real-time warning coefficient that is about to trigger the warning signal is calculated by comparing the difference between the coefficient of each group of cases included in the corresponding dynamic warning threshold range and taking the absolute value to obtain the case proximity coefficient. The case with the smallest case proximity coefficient is selected, and the handling record case is extracted from it and sent to the operator.

[0015] Intelligent monitoring systems for zero-discharge landfill leachate systems include: Multi-source data acquisition and processing module: used to collect operating parameters of biochemical treatment process, membrane treatment process and crystallization treatment process in zero emission system in real time, clean, normalize and time-series aligned the collected data, integrate it into health dataset, and split it into biochemical treatment process subset, membrane treatment process subset and crystallization treatment process subset according to process type; Operating condition type identification module: It is used to collect the water inflow load parameters, operation control parameters and environmental status parameters of the current time zone to form a real-time operating condition set, call the pre-stored reference operating condition set, calculate the single parameter similarity through Euclidean distance and weighted fusion to obtain the comprehensive similarity, and compare it with the set threshold to determine the current operating condition type of the system. Dynamic early warning threshold construction module: It is used to establish a historical database containing historical health datasets, maintenance records and alarm events. Through early warning learning logic, it extracts alarm datasets and benchmark cases of different process types under different operating conditions, calculates the early warning coefficient of each process, and constructs the corresponding dynamic early warning threshold range. Monitoring and evaluation execution module: It is used to classify real-time health datasets by process type and match them with the current working conditions, calculate real-time early warning coefficients and compare them with dynamic early warning threshold ranges, and trigger corresponding early warning signals.

[0016] The technical effects and advantages of this invention are as follows: (1) The adaptability of working conditions is significantly improved, the drawbacks of fixed thresholds are solved, the working condition type is accurately identified by calculating the comprehensive similarity through Euclidean distance, and dynamic early warning threshold ranges are constructed for different working conditions to avoid false alarms or missed alarms caused by fluctuations in influent load and changes in ambient temperature, so that the monitoring standards are accurately matched with the actual operating status and the zero-emission system is guaranteed to operate stably. (2) The accuracy of early warning has been greatly improved, potential risks can be identified in advance, the core operating indicators of each process can be integrated, the early warning coefficient can be calculated through multi-dimensional parameters, and an early warning mechanism related to process and operating conditions can be established. This can accurately capture hidden dangers such as sludge health deterioration, membrane fouling, and unstable crystallization, change the single parameter exceeding the standard judgment mode, shorten the early warning response lag time, and reduce the probability of failure. (3) Operation and maintenance efficiency and intelligence level are improved simultaneously. When an early warning is issued, historical handling cases of similar working conditions are automatically retrieved to provide decision-making reference for operators and shorten the fault location and handling cycle. At the same time, historical health data, maintenance records, etc. are integrated to continuously optimize the early warning standards through data learning, reduce the cost of manual intervention, and promote the intelligent iteration and upgrading of the monitoring system. Attached Figure Description

[0017] Figure 1 This is a flowchart of the intelligent monitoring method for a landfill leachate zero-discharge system according to the present invention; Figure 2 This is a schematic diagram of the intelligent monitoring system for zero-discharge landfill leachate systems according to the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1 like Figure 1 As shown, the intelligent monitoring method for a landfill leachate zero-discharge system includes: Multi-source data processing: Real-time collection of operating parameters for different process types in the landfill leachate zero-discharge system, followed by data cleaning, normalization, and time-series alignment, and integration into a health dataset; Process types include biochemical treatment processes, membrane treatment processes, and crystallization treatment processes; Biochemical treatment process parameters include activated sludge health status index, nitrification efficiency deviation, and carbon-nitrogen ratio imbalance coefficient; Membrane treatment process parameters include fouling rate, desalination rate attenuation coefficient, and energy consumption ratio; The crystallization process parameters include the evaporator heating chamber temperature and the evaporator vacuum level; Based on the three major process types determined in the pretreatment stage, the health dataset is directly split into three independent datasets: "Biochemical Treatment Process Subset", "Membrane Treatment Process Subset", and "Crystallization Treatment Process Subset". Each subset contains only the characteristic parameters of the corresponding process. For example, the biochemical treatment process subset only retains the time-series data of three parameters: activated sludge health status index, nitrification efficiency deviation, and carbon-nitrogen ratio imbalance coefficient, to ensure a strong correlation between the data and the process.

[0020] Operating condition type determination: Real-time collection of influent load parameters, operation control parameters and environmental status parameters of the landfill leachate zero discharge system in the current time zone as a real-time operating condition set. Pre-construct reference operating condition sets corresponding to different operating condition types. Comprehensive evaluation of the real-time operating condition set in the current time zone and the reference operating condition sets of each operating condition type to determine the current operating condition type of the system. The operating conditions include, but are not limited to, low-load stable operating conditions and high-load impact operating conditions, which are specifically preset by technical personnel. For example, Low-load stable operating conditions: the inlet water flow rate is 50%-70% of the design value; the membrane recovery rate and evaporator feed concentration are set to normal values; the ambient temperature is stable at 20-25℃. High-load shock conditions: Influent flow rate and COD / ammonia nitrogen concentration exceed 120% of the design value (such as leachate flushing after heavy rain); membrane recovery rate is reduced and evaporator feed concentration is increased.

[0021] Specifically: The influent load parameters include influent flow rate, influent COD concentration, influent ammonia nitrogen concentration, and influent conductivity; Operating control parameters include membrane system recovery rate settings and evaporator feed concentration settings; The environmental condition parameter is the ambient temperature; The reference operating condition set includes influent load reference parameters, operation control reference parameters, and environmental condition reference parameters for the current operating condition type. Using Euclidean distance, the single-parameter similarity between the real-time operating condition set and the reference operating condition set is calculated. After weighted fusion, the comprehensive similarity between the real-time operating condition set and each set of reference operating conditions is calculated. The comprehensive similarity is compared with the set similarity threshold. If there is a set of comprehensive similarities below the threshold, the operating condition type is identified as the current operating condition type of the system. If there are multiple sets of comprehensive similarities below the threshold, the operating condition type with the lowest comprehensive similarity is identified as the current operating condition type of the coefficient. If the overall similarity of each group is higher than the threshold, an intervention signal is triggered and sent to the technicians, who then intervene to determine the current working condition type.

[0022] The process of single-parameter similarity calculation, That is, through the formula Calculate the influent load similarity Operation control similarity and environmental similarity ; Where i represents the number of the influent flow rate, influent COD concentration, influent ammonia nitrogen concentration, and influent conductivity. For the influent load parameters of the real-time operating condition set, The influent load parameters are for reference operating conditions. and These represent the membrane system recovery rate setting and the evaporator feed concentration setting in the real-time operating condition set, respectively. and These represent the membrane system recovery rate setting and the evaporator feed concentration setting, respectively, for the reference operating condition set; and These represent the ambient temperatures of the real-time operating condition set and the reference operating condition set, respectively.

[0023] Weighted fusion process, That is, using formulas Calculate the overall similarity ;in , , For influent load similarity Operation control similarity and environmental similarity The weighting coefficients are equal to one.

[0024] Early warning system construction: Establish a historical database containing historical health datasets, maintenance records and alarm events. Based on the historical database, use early warning learning logic to process the data and construct dynamic early warning threshold ranges for different process types under different operating conditions. Specifically: Retrieve the case number of all alarm events from the historical database and integrate them into an alarm case set. Integrate cases other than alarm events into a reference case set. : Match relevant alarm cases to their respective process types within the alarm case set to form biochemical case sets, membrane case sets, and crystallization case sets; Historical health datasets within a set time zone prior to the alarm occurrence are extracted from relevant alarm cases of different process types and used as alarm datasets. The reference case set includes pre-marked cases for different process types under different operating conditions, serving as benchmark cases; Technical personnel will label benchmark cases on reference datasets for different process types under different operating conditions, which will serve as a reference for subsequent dynamic early warning threshold ranges.

[0025] For different process types, a comprehensive analysis is conducted by combining alarm datasets of all processes under the same operating conditions and corresponding benchmark cases to construct dynamic early warning threshold ranges for different process types under different operating conditions. For biochemical treatment processes, the sludge concentration, sludge settling ratio, and dissolved oxygen at the aerobic tank outlet within a set time zone before the alarm occurred in each case were extracted from biochemical case studies under different operating conditions. The average values ​​were then calculated and used as the alarm concentration, alarm settling ratio, and alarm dissolved oxygen for each case under different operating conditions. Sludge concentration, as a core indicator reflecting sludge quantity, directly affects the number of microbial populations and their metabolic capacity.

[0026] The sludge settling ratio directly characterizes the settling performance of sludge and is a key parameter for judging the stability of sludge floc structure.

[0027] Dissolved oxygen is a necessary condition for the metabolic activities of aerobic microorganisms, and is especially crucial for the growth and reproduction of autotrophic bacteria such as nitrifying bacteria.

[0028] Benchmark cases of biochemical treatment processes under different operating conditions were extracted from the reference case collection. Sludge concentration, sludge settling ratio and dissolved oxygen were extracted from the benchmark cases as normal concentration, normal settling ratio and normal dissolved oxygen. After comprehensively processing the alarm concentration, alarm settling ratio, and alarm dissolved oxygen under different operating conditions, and combining them with the normal concentration, normal settling ratio, and normal dissolved oxygen, the sludge health status index under different operating conditions is output. Detailed explanation: The alarm concentration, alarm sedimentation ratio, and alarm dissolved oxygen will be marked as follows: , , Where 'a' represents the operating condition number; Normal concentration, normal sedimentation ratio, and normal dissolved oxygen are respectively labeled as , , ; Using formula Calculations were performed to obtain the sludge health status index; among which... , as well as The weighting coefficients are set, and their sum is one.

[0029] Extract the actual nitrification efficiency within the set time zone before the alarm occurs for each case; where the actual nitrification efficiency = (influent ammonia nitrogen concentration - effluent ammonia nitrogen concentration) / influent ammonia nitrogen concentration × 100%; after averaging, it is used as the average nitrification efficiency for each case under different operating conditions. The actual nitrification efficiency under different operating conditions is extracted from the benchmark case and used as a reference efficiency. After calculating by |average nitrification efficiency - reference efficiency| / reference efficiency, the deviation of nitrification efficiency under different operating conditions is output. Nitrification efficiency is the core indicator for the removal of ammonia nitrogen through biochemical treatment, and deviation is used to quantify the difference between the actual nitrification efficiency and the reference efficiency.

[0030] Extract the influent COD concentration and total nitrogen concentration within the set time zone before the alarm occurs for each case, and calculate the average values ​​to obtain the average COD concentration and average total nitrogen concentration for each case under different operating conditions. The carbon-nitrogen ratio is a key nutrient balance indicator that affects microbial growth, and the imbalance coefficient is used to determine the degree of deviation between the actual value and the reference value.

[0031] The influent COD concentration and total nitrogen concentration under different operating conditions were extracted from the benchmark case and used as reference COD concentration and reference total nitrogen concentration. pass: The calculation is as follows: |(Average COD concentration / Average total nitrogen concentration)-(Reference COD concentration / Reference total nitrogen concentration)| / (Reference COD concentration / Reference total nitrogen concentration) outputs the carbon-nitrogen ratio imbalance coefficient under different operating conditions. After comprehensively processing the sludge health status index, nitrification efficiency deviation, and carbon-nitrogen ratio imbalance coefficient of each case under different operating conditions, the biochemical early warning coefficient of each case under different operating conditions is output. Detailed explanation: That is, through the formula Calculate the biochemical early warning coefficient ;in and These represent the deviation of nitrification efficiency and the carbon-nitrogen ratio imbalance coefficient, respectively. The weighting coefficients are set, and their sum is one.

[0032] Extract the biochemical early warning coefficients of each group belonging to the same working condition, locate the highest and lowest coefficient values ​​respectively, and construct the interval to obtain the dynamic early warning threshold intervals corresponding to different working conditions under the biochemical treatment process.

[0033] For membrane treatment processes, the transmembrane pressure difference within a set time zone before the alarm occurs in each case is extracted from a collection of membrane cases under different operating conditions; that is, it is obtained by subtracting the membrane module outlet pressure from the membrane module inlet pressure. Using formula The contamination rate for each case under different operating conditions was calculated; whereby and These represent the real-time transmembrane pressure difference at the end and beginning of the set time zone, respectively. Time zone duration; Membrane fouling is a core factor affecting membrane lifespan, and the fouling rate is quantified by the rate of change of transmembrane pressure difference.

[0034] The desalination rate of each membrane case under different operating conditions within a set time zone before the alarm occurred was extracted; where the desalination rate = (feed water conductivity - product water conductivity) / feed water conductivity × 100%; Using formula The desalination rate attenuation coefficient for each case under different operating conditions was calculated; where and These represent the desalination rates at the initial and final time points of the set time zone, respectively. Desalination rate is the core efficiency indicator of membrane separation, and the attenuation coefficient is used to quantify the difference between the actual desalination rate and the initial desalination rate.

[0035] The energy consumption ratio of each case within a set time zone before the alarm occurs is extracted from the membrane case set under different operating conditions; that is, it is calculated by dividing the real-time power consumption of the membrane unit by the real-time water production of the membrane unit. Energy consumption ratio is a core indicator of the economic efficiency of membrane unit operation, and anomaly is used to judge the degree of deviation between the actual energy consumption ratio and the theoretical energy consumption ratio.

[0036] Based on the fouling rate, desalination rate attenuation coefficient, and energy consumption ratio of each case under different operating conditions, the fouling rate, desalination rate attenuation coefficient, and energy consumption ratio under different operating conditions are extracted from the benchmark case as reference rate, reference attenuation coefficient, and reference energy consumption ratio. After comprehensive processing, the membrane warning coefficient of each case under different operating conditions is output. Detailed explanation: The pollution rate, desalination rate attenuation coefficient, and energy consumption ratio are respectively labeled as , , ; The reference rate, reference attenuation coefficient, and reference energy ratio are respectively labeled as , , ; Using formula Calculations were performed to obtain the membrane early warning coefficient. ;in , , The weighting coefficients are set, and their sum is one.

[0037] Extract the membrane warning coefficients of each group belonging to the same operating condition, locate the highest and lowest coefficient values ​​respectively, and construct the interval to obtain the dynamic warning threshold intervals corresponding to different operating conditions under the membrane treatment process.

[0038] For the crystallization process, the evaporator heating chamber temperature and evaporator vacuum degree within a set time zone before the alarm occurs in each case are extracted from the crystallization case set under different operating conditions. The temperature fluctuation value is calculated by taking the absolute value and averaging the difference between the heating chamber temperature and the set temperature at each time point. For the difference between the vacuum level of the evaporation chamber and the set vacuum value at each time point, the absolute value is taken and the average value is calculated to obtain the vacuum fluctuation value. The stability of the crystallization process is quantified by the fluctuation of key thermal parameters (temperature) in the evaporation crystallization unit.

[0039] Based on the temperature fluctuation and vacuum fluctuation values ​​of each case under different operating conditions, the temperature fluctuation and vacuum fluctuation values ​​under different operating conditions are extracted from the benchmark case as reference temperature fluctuation and reference vacuum fluctuation. After comprehensive processing, the crystallization warning coefficient of each case under different operating conditions is output. Detailed explanation: The temperature fluctuation value and the vacuum fluctuation value are respectively marked as , ; Reference temperature fluctuation and reference vacuum fluctuation are respectively denoted as , ; Using formula Calculations were performed to obtain the crystallization early warning coefficient. ;in , The weighting coefficients are set, and their sum is one.

[0040] Extract the crystallization warning coefficients of each group belonging to the same working condition, locate the highest and lowest coefficient values ​​respectively, and construct the interval to obtain the dynamic warning threshold intervals corresponding to different working conditions under the crystallization process.

[0041] Monitoring, evaluation and processing: After classifying the real-time collected health dataset according to different process types, the corresponding working condition type is identified and the corresponding dynamic early warning threshold range is entered for matching. If the matching is successful, an early warning signal is triggered. When the early warning is triggered, the handling record cases of the same working condition in the historical database are automatically retrieved for operators to refer to. Specifically: After identifying the operating condition type, the alarm dataset is replaced with the current health dataset. Then, the biochemical warning coefficient, membrane warning coefficient, and crystallization warning coefficient are calculated based on the corresponding benchmark case to form a real-time warning coefficient set. The set is then input into the corresponding dynamic warning threshold range for matching. If any coefficient in the real-time warning coefficient set is within the corresponding dynamic warning threshold range, the warning signal for that coefficient is triggered. The warning signals include biochemical warning signals, membrane warning signals, and crystallization warning signals, which correspond to the biochemical warning coefficient, membrane warning coefficient, and crystallization warning coefficient, respectively.

[0042] The real-time warning coefficient that is about to trigger the warning signal is calculated by comparing the difference between the coefficient of each group of cases included in the corresponding dynamic warning threshold range and taking the absolute value to obtain the case proximity coefficient. The case with the smallest case proximity coefficient is selected, and the handling record case is extracted from it and sent to the operator.

[0043] The above formulas are all dimensionless calculations. Dimensionless calculations can be performed using various methods such as standardization, which will not be elaborated here. The formulas are derived from software simulations based on a large amount of collected data, and the preset parameters in the formulas can be set by those skilled in the art according to the actual situation.

[0044] Example 2 Please see Figure 2 As shown, based on the intelligent monitoring method for a landfill leachate zero discharge system provided in Embodiment 1 of this application, Embodiment 2 of this application proposes an intelligent monitoring system for a landfill leachate zero discharge system. Embodiment 2 is merely a preferred embodiment of Embodiment 1, and the implementation of Embodiment 2 will not affect the separate implementation of Embodiment 1.

[0045] Specifically, the intelligent monitoring system for a landfill leachate zero-discharge system provided in Embodiment 2 of this application includes: Multi-source data acquisition and processing module: used to collect operating parameters of biochemical treatment process, membrane treatment process and crystallization treatment process in zero emission system in real time, clean, normalize and time-series aligned the collected data, integrate it into health dataset, and split it into biochemical treatment process subset, membrane treatment process subset and crystallization treatment process subset according to process type; Operating condition type identification module: It is used to collect the water inflow load parameters, operation control parameters and environmental status parameters of the current time zone to form a real-time operating condition set, call the pre-stored reference operating condition set, calculate the single parameter similarity through Euclidean distance and weighted fusion to obtain the comprehensive similarity, and compare it with the set threshold to determine the current operating condition type of the system. Dynamic early warning threshold construction module: It is used to establish a historical database containing historical health datasets, maintenance records and alarm events. Through early warning learning logic, it extracts alarm datasets and benchmark cases of different process types under different operating conditions, calculates the early warning coefficient of each process, and constructs the corresponding dynamic early warning threshold range. Monitoring and evaluation execution module: It is used to classify real-time health datasets by process type and match them with the current working conditions, calculate real-time early warning coefficients and compare them with dynamic early warning threshold ranges, and trigger corresponding early warning signals.

[0046] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, ATA hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state ATA hard disk.

[0047] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0048] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0049] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0050] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0051] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0052] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable ATA hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0053] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An intelligent monitoring method for landfill leachate zero-discharge systems, characterized in that, include: Step 1: Collect operating parameters of different process types in the landfill leachate zero-discharge system in real time and integrate them into a health dataset; Step 2: Collect in real time the influent load parameters, operation control parameters and environmental status parameters of the landfill leachate zero discharge system in the current time zone as a real-time operating condition set. Pre-construct reference operating condition sets corresponding to different operating condition types. Conduct a comprehensive evaluation of the real-time operating condition set in the current time zone and the reference operating condition sets of each operating condition type to determine the current operating condition type of the system. Step 3: Establish a historical database containing historical health datasets, maintenance records, and alarm events. Based on the historical database, use early warning learning logic to process the data and construct dynamic early warning threshold ranges for different process types under different operating conditions. Step 4: After classifying the real-time collected health dataset according to different process types, identify the type of operating condition and input it into the corresponding dynamic early warning threshold range for matching. If the match is successful, an early warning signal is triggered.

2. The intelligent monitoring method for a landfill leachate zero-discharge system according to claim 1, characterized in that: The process type and operating parameters in step one include: Process types include biochemical treatment processes, membrane treatment processes, and crystallization treatment processes; Biochemical treatment process parameters include activated sludge health status index, nitrification efficiency deviation, and carbon-nitrogen ratio imbalance coefficient; Membrane treatment process parameters include fouling rate, desalination rate attenuation coefficient, and energy consumption ratio; The crystallization process parameters include the evaporator heating chamber temperature and the evaporator vacuum degree.

3. The intelligent monitoring method for a landfill leachate zero-discharge system according to claim 1, characterized in that: Step two is the process of determining the type of operating condition. The influent load parameters include influent flow rate, influent COD concentration, influent ammonia nitrogen concentration, and influent conductivity; Operating control parameters include membrane system recovery rate settings and evaporator feed concentration settings; The environmental condition parameter is the ambient temperature; The reference operating condition set includes influent load reference parameters, operation control reference parameters, and environmental condition reference parameters for the current operating condition type. Using Euclidean distance, the single-parameter similarity between the real-time working condition set and the reference working condition set is calculated. After weighted fusion, the comprehensive similarity between the real-time working condition set and each set of reference working conditions is calculated. The comprehensive similarity is compared with the set similarity threshold. Among the sets of comprehensive similarities below the threshold, the working condition type with the lowest comprehensive similarity is identified as the working condition type of the current coefficient.

4. The intelligent monitoring method for a landfill leachate zero-discharge system according to claim 2, characterized in that: The logic for constructing the dynamic early warning threshold range in step three; Retrieve the case number of all alarm events from the historical database and integrate them into an alarm case set. Integrate cases other than alarm events into a reference case set. : Match relevant alarm cases to their respective process types within the alarm case set to form biochemical case sets, membrane case sets, and crystallization case sets; Historical health datasets within a set time zone prior to the alarm occurrence are extracted from relevant alarm cases of different process types and used as alarm datasets. The reference case set contains pre-marked cases for different process types under different operating conditions, serving as benchmark cases; For different process types, a comprehensive analysis is conducted by combining alarm datasets of all processes under the same operating conditions and corresponding benchmark cases to construct dynamic early warning threshold ranges for different process types under different operating conditions.

5. The intelligent monitoring method for a landfill leachate zero-discharge system according to claim 4, characterized in that: The dynamic early warning threshold range corresponding to different operating conditions under biochemical treatment processes is constructed. From a collection of biochemical cases under different operating conditions, the sludge concentration, sludge settling ratio, dissolved oxygen, actual nitrification efficiency, influent COD concentration, and influent total nitrogen concentration of the set time zone before the alarm were extracted. The alarm concentration, alarm settling ratio, alarm dissolved oxygen, average nitrification efficiency, average COD concentration, and average total nitrogen concentration of each case were calculated by averaging. From the baseline cases in the reference case set, extract the normal concentration, normal sedimentation ratio, normal dissolved oxygen, reference efficiency, reference COD concentration, and reference total nitrogen concentration for the corresponding operating conditions. Sludge health status index: obtained by comprehensively processing alarm concentration, alarm settling ratio, alarm dissolved oxygen, normal concentration, normal settling ratio, and normal dissolved oxygen; Nitrification efficiency deviation: |Average nitrification efficiency - Reference efficiency| / Reference efficiency; Carbon-to-nitrogen ratio imbalance coefficient: |Actual carbon-to-nitrogen ratio - Reference carbon-to-nitrogen ratio| / Reference carbon-to-nitrogen ratio; where carbon-to-nitrogen ratio = COD concentration / total nitrogen concentration; The sludge health status index, nitrification efficiency deviation, and carbon-nitrogen ratio imbalance coefficient are comprehensively processed to output the biochemical early warning coefficient for each case under different working conditions. The biochemical warning coefficients of all cases under the same working condition are summarized, and the dynamic warning threshold range corresponding to the working condition is constructed by using its highest and lowest values ​​as boundaries.

6. The intelligent monitoring method for a landfill leachate zero-discharge system according to claim 5, characterized in that: Dynamic early warning threshold ranges corresponding to different operating conditions under the membrane treatment process in China; From a collection of membrane case studies under different operating conditions, we extracted the transmembrane pressure difference, desalination rate, and energy consumption ratio for the set time zone before the alarm. Through formula Calculate the pollution rate; where and These represent the real-time transmembrane pressure difference at the end and beginning of the set time zone, respectively. Time zone duration; Using formula The desalination rate attenuation coefficient for each case under different operating conditions was calculated; where and These represent the desalination rates at the initial and final time points of the set time zone, respectively. Extract the reference rate, reference attenuation coefficient, and reference energy consumption ratio for the corresponding operating conditions from the benchmark cases in the reference case set. After combining the fouling rate, desalination rate attenuation coefficient, and energy consumption ratio, the membrane early warning coefficient for each case was obtained. The membrane early warning coefficients of all cases under the same working condition are summarized, and the dynamic early warning threshold range corresponding to the working condition is constructed by using its highest and lowest values ​​as boundaries.

7. The intelligent monitoring method for a landfill leachate zero-discharge system according to claim 6, characterized in that: The dynamic early warning threshold range corresponding to different operating conditions under the membrane crystallization process is constructed in China; From the collection of crystallization cases under different operating conditions, the evaporator heating chamber temperature and evaporator vacuum degree of the set time zone before the alarm were extracted; the absolute value of the difference between the measured value and the set value at each time point was calculated, and then the temperature fluctuation value and vacuum degree fluctuation value were obtained by averaging. The reference temperature fluctuation and reference vacuum fluctuation under different operating conditions are extracted from the benchmark case. After comprehensive processing of the temperature fluctuation value and vacuum fluctuation value, the crystallization warning coefficient of each case under different operating conditions is output. The crystallization warning coefficients of all cases under the same working condition are summarized, and the dynamic warning threshold range corresponding to the working condition is constructed by using its highest and lowest values ​​as boundaries.

8. The intelligent monitoring method for a landfill leachate zero-discharge system according to claim 7, characterized in that: The specific logic for triggering the warning signal in step four; After identifying the type of working condition, the alarm dataset is replaced with the current health dataset. The biochemical warning coefficient, membrane warning coefficient, and crystallization warning coefficient are calculated in combination with the corresponding benchmark case to form a real-time warning coefficient set. The set is then matched with the corresponding dynamic warning threshold range. If any coefficient in the real-time warning coefficient set is within the corresponding dynamic warning threshold range, the warning signal of the corresponding coefficient is triggered.

9. The intelligent monitoring method for a landfill leachate zero-discharge system according to claim 7, characterized in that: The system automatically retrieves case records of similar situations from the historical database when an early warning signal is triggered. The real-time warning coefficient that is about to trigger the warning signal is calculated by comparing the difference between the coefficient of each group of cases included in the corresponding dynamic warning threshold range and taking the absolute value to obtain the case proximity coefficient. The case with the smallest case proximity coefficient is selected, and the handling record case is extracted from it and sent to the operator.

10. An intelligent monitoring system for a landfill leachate zero-discharge system, applied to the intelligent monitoring method for a landfill leachate zero-discharge system as described in any one of claims 1-9, characterized in that, include: Multi-source data acquisition and processing module: used to collect operating parameters of biochemical treatment process, membrane treatment process and crystallization treatment process in zero emission system in real time, clean, normalize and time-series aligned the collected data, integrate it into health dataset, and split it into biochemical treatment process subset, membrane treatment process subset and crystallization treatment process subset according to process type; Operating condition type identification module: It is used to collect the water inflow load parameters, operation control parameters and environmental status parameters of the current time zone to form a real-time operating condition set, call the pre-stored reference operating condition set, calculate the single parameter similarity through Euclidean distance and weighted fusion to obtain the comprehensive similarity, and compare it with the set threshold to determine the current operating condition type of the system. Dynamic early warning threshold construction module: It is used to establish a historical database containing historical health datasets, maintenance records and alarm events. Through early warning learning logic, it extracts alarm datasets and benchmark cases of different process types under different operating conditions, calculates the early warning coefficient of each process, and constructs the corresponding dynamic early warning threshold range. Monitoring and evaluation execution module: It is used to classify real-time health datasets by process type and match them with the current working conditions, calculate real-time early warning coefficients and compare them with dynamic early warning threshold ranges, and trigger corresponding early warning signals.

Images