An intelligent marine sewage discharge monitoring method and system

Abstract

The present application relates to the technical field of ship sewage monitoring, and provides an intelligent ship sewage monitoring method and system. The method includes: obtaining the sewage treatment stage of the target ship; collecting treatment samples of the sewage treatment stage under a preset time zone, and training a multi-stage sewage model; collecting initial pollutant state information, inputting model analysis, generating treatment parameters and predicted quality parameters; generating control signals with treatment parameters, controlling sewage equipment, and collecting multi-stage state data; verifying the state data and predicted quality parameters to generate verification results; locating abnormal stage sequences, performing abnormal attenuation analysis, locating target abnormal stages, and generating abnormal reminder information. The present application solves the technical problems that multiple continuous treatment stages are difficult to effectively monitor and abnormalities are difficult to locate during ship sewage discharge, realizes intelligent and automated sewage monitoring, and improves the efficiency and accuracy of sewage treatment.

Description

Technical Field

[0001] The present application relates to the field of marine environmental protection technology, specifically to the field of ship sewage discharge monitoring technology, and in particular to an intelligent ship sewage discharge monitoring method and system. Background Art

[0002] With the booming development of the global shipping industry, ship sewage control has become a key link in protecting the marine environment. However, in the ship sewage discharge process, due to the existence of multiple continuous treatment stages, the operating status and treatment effect of each stage will affect the final sewage quality. Traditional ship sewage monitoring methods rely on regular inspections, but this method is not only inefficient, but also difficult to achieve effective monitoring and abnormal location of multiple continuous treatment stages, and cannot meet the modern shipping industry's demand for efficient, accurate and safe sewage management. Summary of the invention

[0003] The present application provides an intelligent method and system for monitoring ship sewage discharge, aiming to solve the technical problems that multiple continuous treatment stages are difficult to effectively monitor and abnormalities are difficult to locate during the ship sewage discharge process.

[0004] In view of the above problems, the present application provides an intelligent ship sewage discharge monitoring method and system.

[0005] The first aspect disclosed in the present application provides an intelligent ship sewage discharge monitoring method, which includes: obtaining multiple continuous sewage discharge treatment stages for treating a first pollutant on a target ship; collecting pollutant treatment samples of the multiple continuous sewage discharge treatment stages in a preset time zone, and training a multi-stage sewage discharge analysis model; collecting pollutant state information of the initial pollutant received in the initial treatment stage and inputting it into the multi-stage sewage discharge analysis model for sewage discharge treatment analysis, generating multi-stage treatment parameters and multi-stage predicted treatment quality parameters; generating a control signal with the multi-stage treatment parameters to control the first sewage discharge equipment of the first pollutant, and collecting multi-stage state monitoring data under the multiple continuous sewage discharge treatment stages; performing stage alignment verification on the multi-stage state monitoring data and the multi-stage predicted treatment quality parameters to generate a multi-stage verification result; locating the initial abnormal stage sequence based on the multi-stage verification result, and performing abnormal attenuation analysis on the initial abnormal stage sequence, locating the target abnormal stage, and generating abnormal reminder information for the target abnormal stage.

[0006] Another aspect disclosed in the present application provides an intelligent ship sewage monitoring system, the system comprising: a processing stage acquisition module, the processing stage acquisition module is used to acquire multiple continuous sewage treatment stages for treating a first pollutant on a target ship; a model training module, the model training module is used to collect pollutant treatment samples of the multiple continuous sewage treatment stages in a preset time zone, and train a multi-stage sewage analysis model; a processing analysis module, the processing analysis module is used to collect pollutant state information of initial pollutants received in the initial processing stage and input it into the multi-stage sewage analysis model for sewage treatment analysis, and generate multi-stage processing parameters and multi-stage predicted processing quality parameters; An equipment control module, the equipment control module is used to generate a control signal with the multi-stage processing parameters, control the first sewage discharge equipment of the first pollutant, and collect multi-stage status monitoring data under the multiple continuous sewage treatment stages; an alignment verification module, the alignment verification module is used to perform a stage alignment verification on the multi-stage status monitoring data and the multi-stage predicted processing quality parameters to generate a multi-stage verification result; an attenuation analysis module, the attenuation analysis module is used to locate the initial abnormal stage sequence based on the multi-stage verification result, and perform abnormal attenuation analysis on the initial abnormal stage sequence, locate the target abnormal stage, and generate abnormal reminder information for the target abnormal stage.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The above-mentioned intelligent ship sewage monitoring method collects treatment samples of multiple continuous stages for treating pollutants on the ship, and trains a multi-stage model capable of analyzing the sewage treatment process through these data. Subsequently, the state information of the initial pollutants is collected in real time, and the trained model is used for analysis to predict the treatment parameters and expected treatment quality of each stage. After that, based on these predicted parameters, a control signal is generated to guide the operation of the sewage discharge equipment, and the state data of the entire treatment process is continuously monitored. Then, the actual state data is compared and verified with the predicted treatment quality parameters to ensure that the treatment process is consistent with expectations. Once a deviation between the actual state and the prediction is found, the stage where these abnormalities occur is located. Through further abnormal attenuation analysis, the target abnormal stage is accurately identified, and a reminder message is generated so that timely measures can be taken to deal with it. This method not only improves the efficiency and accuracy of sewage treatment, but also can quickly discover and deal with abnormal situations, providing strong technical support for the environmental protection operation of ships.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of a flow chart of an intelligent ship sewage discharge monitoring method in an embodiment;

[0012] Figure 2 The present invention is an architecture diagram of an intelligent marine sewage discharge monitoring system in one embodiment.

[0013] Explanation of the accompanying drawings: processing stage acquisition module 1, model training module 2, processing analysis module 3, equipment control module 4, alignment verification module 5, attenuation analysis module 6. DETAILED DESCRIPTION

[0014] The embodiments of the present application provide an intelligent method and system for monitoring ship sewage discharge, thereby solving the technical problems that multiple continuous processing stages in the ship sewage discharge process are difficult to effectively monitor and anomalies are difficult to locate.

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0016] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the present application provides an intelligent marine sewage discharge monitoring method, the method comprising:

[0019] Obtaining a plurality of consecutive blowdown treatment stages for treating a first pollutant on a target vessel;

[0020] With the prosperity of global trade and the development of shipping industry, the number of ships has increased rapidly, and the pollutants they discharge have posed an increasingly serious threat to the marine environment. During navigation and berthing, ships will discharge a large amount of oily sewage, exhaust gas and other harmful substances. These pollutants not only directly threaten the survival and reproduction of marine life, but may also affect human health through the food chain.

[0021] In an embodiment of the present application, on the target ship, the treatment of the first pollutant involves multiple continuous and complex sewage treatment stages. These treatment stages cover the treatment processes of different types of pollutants, including the separation and purification of oily pollutants, the collection and treatment of domestic pollutants, the compression and classification of solid waste, and the emission control of ship exhaust. Each treatment stage has its specific treatment technology and equipment to ensure that different types of pollutants are effectively and in compliance with environmental standards. For example, oily pollutants need to pass through an oil-water separation chamber for oil-water separation, and then pass through an oxidation chamber and other steps to remove residual oil; ship exhaust is treated through oxidation chambers, treatment chambers and other steps to reduce harmful gas emissions. Through these continuous sewage treatment stages, the target ship can achieve comprehensive, efficient and environmentally friendly treatment of different pollutants, thereby protecting the marine environment.

[0022] Collect pollutant treatment samples of the multiple continuous sewage treatment stages in a preset time zone, and train a multi-stage sewage analysis model;

[0023] In one embodiment, during the ship sewage monitoring process, the system terminal first collects pollutant treatment samples of each continuous sewage treatment stage within a preset time period. These sample data cover the treatment samples of different types of pollutants such as oily pollutants, domestic pollutants, solid waste and ship exhaust at different treatment stages, including initial pollutant state samples, multi-stage treatment parameter samples and multi-stage predicted quality samples. Subsequently, the system terminal uses the treatment samples to train the multi-stage sewage analysis model. Through continuous learning and adjustment, the model can gradually improve its predictive ability for the treatment of pollutants at different treatment stages, providing strong data support for subsequent sewage monitoring. Afterwards, the trained model is connected to a multi-stage performance decay feedback network constructed based on a Markov chain for feedback optimization of the output of the multi-stage sewage analysis model.

[0024] Furthermore, the present application provides a method for collecting pollutant treatment samples of the plurality of continuous sewage treatment stages in a preset time zone and training a multi-stage sewage analysis model, including:

[0025] The preset time zone includes time intervals under multiple equipment maintenance nodes, the pollutant treatment samples include multiple treatment samples under multiple equipment maintenance nodes, and any treatment sample includes an initial pollutant state sample, a multi-stage treatment parameter sample, and a multi-stage predicted quality sample;

[0026] Extracting the first processed sample under the equipment maintenance node closest to the current moment, and training and constructing the multi-stage sewage analysis model;

[0027] Preferably, the preset time zone is divided into a time interval containing multiple equipment maintenance nodes. These maintenance nodes represent the time points for maintenance or calibration of the sewage treatment equipment. In order to train the multi-stage sewage analysis model, the system terminal collects multiple treatment samples corresponding to these equipment maintenance nodes. Each treatment sample records in detail the predicted quality data from the initial pollutant state to the multi-stage treatment, as well as the parameters used in these treatment processes. In order to obtain the most accurate and latest model prediction capabilities, the system terminal selects the first treatment sample under the equipment maintenance node closest to the current moment as the main source of training data. This is because the latest data can best reflect the current equipment status and sewage treatment effect, which helps to build a more accurate multi-stage sewage analysis model. Subsequently, the system terminal pre-processes the selected treatment samples, including steps such as data cleaning and format conversion. Ensure the quality and consistency of the data so that subsequent model training can proceed smoothly. Then extract key features from the pre-processed data, which can reflect the key parameters and status of the sewage treatment process. For example, the concentration of initial pollutants, the operating parameters of the treatment equipment, the treatment time, etc. are extracted as features. After that, the multi-stage pollution analysis model is initialized using the long short-term memory network (LSTM) as a machine learning algorithm. The long short-term memory network can process time series data and capture long-term dependencies in the data, which is important for analyzing continuous pollution treatment stages. Then, the initialized multi-stage pollution analysis model is trained based on the extracted features and predicted quality samples. During the training process, the model learns the mapping relationship from the initial pollutant state and multi-stage treatment parameters to the final pollution treatment quality. After the model training is completed, the system terminal verifies and evaluates the model using an independent validation data set. By comparing the model's prediction results with the predicted quality samples, the performance of the model is evaluated, and indicators such as accuracy and recall are calculated. Then, based on the verification results, the model is optimized and adjusted. This includes adjusting the model's parameters, such as learning rate, hidden layer size, etc. Through continuous optimization, the model's predictive ability and generalization performance are improved. Finally, the trained multi-stage pollution analysis model is output. In summary, by extracting these latest sample data and training the model, it can ensure that the model can accurately predict the effect of future pollution treatment and provide strong support for ship pollution monitoring.

[0028] Using the multiple processing samples under the multiple equipment maintenance nodes to identify the performance degradation of the pollutant treatment equipment, and using the Markov chain to construct a multi-stage performance degradation feedback network;

[0029] The multi-stage performance attenuation feedback network is connected to the multi-stage pollution emission analysis model, and feedback optimization is performed on the output of the multi-stage pollution emission analysis model.

[0030] Preferably, in marine sewage monitoring, equipment performance degradation is an inevitable phenomenon, especially in the continuous sewage treatment process. In order to more accurately predict and treat pollutants, the system terminal must not only rely on historical data to train the model, but also need to consider the degradation of equipment performance. First, multiple processing samples under multiple equipment maintenance nodes are collected. These samples not only record the data of sewage treatment, but also contain the performance status of the equipment after maintenance. By analyzing these samples, N processing parameter sequences under multiple equipment maintenance nodes can be extracted. These processing parameter sequences are used for subsequent processing parameter error calculations under adjacent nodes to identify the performance degradation of the pollutant treatment equipment after each maintenance. In order to further capture the trend of performance degradation, the system terminal uses a Markov chain to construct a multi-stage performance degradation feedback network based on the error calculation results. Markov chain is a probabilistic model that can describe the probability distribution of future states given the current state. By applying Markov chain, it is possible to predict its future performance degradation based on the current state of the equipment and previous maintenance records. Subsequently, the system terminal connects the constructed multi-stage performance degradation feedback network with the multi-stage sewage analysis model. In this way, when the sewage analysis model outputs the prediction results, the performance decay feedback network will adjust and optimize the prediction results based on the current performance status of the equipment. In this way, the effect of sewage treatment can be predicted more accurately and potential equipment performance problems can be discovered in advance. This sewage analysis model combined with a multi-stage performance decay feedback network not only improves the accuracy of the prediction, but also helps users better understand the changes in equipment performance, thereby formulating more reasonable maintenance plans and sewage treatment strategies. This is of great significance for protecting the marine environment and improving the efficiency of ship operations.

[0031] Furthermore, the present application provides for identifying the performance degradation of pollutant treatment equipment using the multiple processing samples under the multiple equipment maintenance nodes, and constructing a multi-stage performance degradation feedback network using a Markov chain. The method also includes:

[0032] Based on the multiple processing samples, the first-stage processing parameter sequence, the second-stage processing parameter sequence, and the N-th-stage processing parameter sequence under the multiple equipment maintenance nodes are extracted with the pollutant states of the adjacent previous stage being consistent as the first constraint condition and the stage control target being consistent as the second constraint condition, wherein N is the total number of stages of the multiple continuous sewage treatment stages;

[0033] Performing processing parameter error calculations at adjacent nodes on the first-stage processing parameter sequence, the second-stage processing parameter sequence, and up to the N-stage processing parameter sequence, respectively, to obtain a first error sequence, a second error sequence, and up to the N-th error sequence;

[0034] Optionally, in order to deeply analyze the performance degradation of ship sewage treatment equipment at different time points, the system terminal performs detailed data analysis and processing based on the treatment samples under multiple equipment maintenance nodes. First, two key constraints are set: the first is that the pollutant status of the adjacent previous stage must be consistent, which is to ensure that the data is comparable in terms of pollutant status; the second is that the stage control target must also be consistent, which is to maintain the stability of the control target during the analysis process. Under the premise of meeting these two constraints, the system terminal extracts the treatment parameter sequence from the first stage to the Nth stage under multiple equipment maintenance nodes, where N is the total number of continuous sewage treatment stages. These parameter sequences record the operating parameters of each treatment stage at different time points, and they are key data for analyzing the performance degradation of the equipment. Subsequently, in the treatment parameter sequence of each stage, the adjacent equipment maintenance nodes are determined. For the treatment parameter sequence of each stage, the treatment parameter errors under adjacent nodes are calculated respectively. This involves calculating the difference between the parameter values ​​of adjacent nodes. Afterwards, the parameter errors between all adjacent nodes calculated in each stage are arranged in order to form the error sequence of that stage. Repeat the above steps, calculate the errors of the processing parameter sequences from the second stage to the Nth stage, and generate the corresponding error sequences. These error sequences intuitively reflect the performance differences of the equipment at different time points. If the equipment performance has not decayed, then theoretically the control parameters should be the same each time, and the values ​​in the error sequence will be very small or close to zero. Through this analysis method, the decay of equipment performance can be more accurately identified, which is of great significance for improving the efficiency of ship sewage treatment and protecting the marine environment.

[0035] Based on the Markov chain, the multi-stage performance decay feedback network is constructed according to the first error sequence, the second error sequence, and up to the Nth error sequence.

[0036] Optionally, after the system terminal obtains multiple error sequences from the first stage to the Nth stage, the concept of Markov chain is used to construct a performance decay feedback network. Specifically, in the Markov chain, the state corresponds to each device maintenance node in each stage. Each state has an error value associated with it, which comes from the corresponding error sequence. For the error sequence of each stage, the transition probability between adjacent nodes is calculated. The transition probability represents the possibility of transitioning from one state to another. Due to the characteristics of the Markov chain, this transition depends only on the current state and does not depend on the previous state. The calculation of the transition probability is based on the state transition frequency in the historical data. For example, if state A often transitions to state B in the past, the state transition frequency from state A to state B is obtained by performing a ratio operation between the number of times state A transitions to state B and the total number of times state A transitions to all possible states. Subsequently, for the error sequence of each stage, a state transition matrix is ​​constructed, in which each element represents the probability of transitioning from one state to another. Then, a Markov chain model is constructed for each stage using the calculated transition probability matrix. These models will be able to describe the attenuation of device performance over time in each stage. Afterwards, the Markov chain models of all stages are integrated to form a multi-stage performance decay feedback network. This network can comprehensively consider the performance decay of multiple stages, and predict the performance status of the equipment at a certain point in the future through the state transition path and probability in the network, providing a comprehensive and dynamic perspective for the system terminal to analyze and predict the changing trend of equipment performance. In summary, by constructing a performance decay feedback network, the severity of equipment performance decay can be more accurately assessed, and more reasonable maintenance plans and performance optimization strategies can be formulated accordingly. This is of great significance for ensuring the stable operation of ship sewage treatment equipment and improving treatment efficiency.

[0037] Collecting pollutant state information of initial pollutants received in the initial treatment stage and inputting it into the multi-stage pollutant analysis model to perform pollutant treatment analysis, and generate multi-stage treatment parameters and multi-stage predicted treatment quality parameters;

[0038] In one embodiment, in the sewage treatment process, the pollutants first enter the initial treatment stage, which is the first step of the entire sewage treatment process and is responsible for receiving the original pollutants without any treatment. In order to effectively manage and optimize the pollutant treatment process, the system terminal collects detailed state information of the pollutants received in the initial treatment stage, which includes the type, concentration, physical properties and chemical properties of the pollutants. Subsequently, the state information of these initial pollutants is input into the multi-stage sewage analysis model that has been constructed. Through the analysis of the multi-stage sewage analysis model and the connected multi-stage performance attenuation feedback network, a series of multi-stage treatment parameters are generated. These parameters guide the treatment operations of each subsequent stage, including the dosage of chemical agents, reaction time, stirring speed, etc., to ensure that the pollutants can be effectively removed or their harmfulness can be reduced. In addition, the model can also predict the quality state that the pollutants will eventually reach after multi-stage treatment, that is, the multi-stage predicted treatment quality parameters. These parameters include the concentration of the pollutants after treatment, the removal rate, the type and quantity of the remaining pollutants, etc., as well as the predicted values ​​for specific indicators. For example, for the solid waste treatment process, the model can predict the particle diameter distribution range of the solid waste after crushing, so as to determine whether it meets the requirements of subsequent treatment or discharge. In this way, the effect of the entire sewage treatment process can be understood in advance, and the treatment parameters can be adjusted according to the predicted results to optimize the treatment effect and ensure that the final discharged pollutants meet the relevant standards and requirements.

[0039] generating a control signal with the multi-stage treatment parameters, controlling a first sewage discharge device for the first pollutant, and collecting multi-stage status monitoring data in the plurality of continuous sewage treatment stages;

[0040] In one embodiment, during the sewage treatment process, after the multi-stage sewage analysis model generates multi-stage treatment parameters according to the state information of the initial pollutants, the system terminal uses these parameters to guide the actual sewage treatment operation. First, based on these multi-stage treatment parameters, the system terminal generates corresponding control signals, and then sends these signals to the first sewage treatment equipment of the first pollutant. The function of the control signal is to guide the sewage treatment equipment how to work according to the predetermined treatment parameters, such as controlling the dosage of the reagent, adjusting the temperature of the reactor, adjusting the stirring speed, etc. In this way, the sewage treatment equipment can accurately perform the predetermined treatment steps to ensure that the pollutants are properly treated. During the entire treatment process, the system terminal will continuously collect multi-stage state monitoring data under multiple continuous sewage treatment stages. These data include various physical parameters, chemical parameters, and equipment operation status. These data reflect the actual operation of each stage in the sewage treatment process, and are an important basis for evaluating the treatment effect and adjusting the treatment parameters. By real-time monitoring and collecting these data, the entire sewage treatment process can be monitored throughout the process to ensure that each treatment stage can be carried out according to the predetermined parameters, thereby ensuring that the final sewage treatment effect reaches the expected goal. At the same time, these data can also provide valuable information for subsequent process optimization and equipment improvement.

[0041] Performing a stage alignment check on the multi-stage state monitoring data and the multi-stage prediction processing quality parameters to generate a multi-stage check result;

[0042] In one embodiment, during the multi-stage sewage treatment process, the system terminal can obtain two types of important data: one is the multi-stage state monitoring data during the actual operation process, which reflects the actual operation of the sewage equipment in each treatment stage and the treatment status of the pollutants in real time; the other is the multi-stage predicted treatment quality parameters obtained based on the initial pollutant state information and the multi-stage sewage analysis model prediction, which represent the expected and theoretical pollutant treatment quality. In order to evaluate whether the actual operation is consistent with the expected effect, the system terminal performs a stage alignment check. This verification process mainly compares the multi-stage state monitoring data with the multi-stage predicted treatment quality parameters to ensure that the two are consistent or similar in the corresponding treatment stage. Specifically, the stage alignment check will compare the state monitoring data of each treatment stage with the corresponding predicted treatment quality parameters, check the difference between the two, calculate the difference of the same indicator, and compare it with the corresponding indicator difference threshold of each stage. If it is within the set threshold range, it is considered that the treatment of this stage is valid, the verification fails, and the next stage is verified. If the difference exceeds the predetermined range, it means that there is a problem with the current stage treatment, and the verification fails. Subsequently, the system terminal summarizes the verification results of each stage to form a multi-stage verification result. These results not only provide an evaluation of the real-time effect of the sewage treatment process, but also provide an important basis for subsequent optimization and adjustment. If the verification results show that there is a problem in a certain stage, the system terminal will adjust the treatment parameters to ensure that the entire sewage treatment process can proceed as expected and ultimately achieve the expected pollutant treatment quality.

[0043] An initial abnormal phase sequence is located based on the multi-phase verification result, and an abnormal attenuation analysis is performed on the initial abnormal phase sequence to locate a target abnormal phase, and abnormal reminder information is generated for the target abnormal phase.

[0044] In one embodiment, in a multi-stage sewage treatment process, after obtaining the multi-stage verification results, the system terminal locates the initial abnormal stage sequence based on the multi-stage verification results, that is, determines which one or more stages first have abnormalities. This is done by traversing multiple consecutive sewage treatment stages, comparing the actual monitoring data with the predicted treatment quality parameters, and combining the verification results. After locating the initial abnormal stage, the system terminal further performs abnormal attenuation analysis on these abnormal stages. The core idea of ​​abnormal attenuation analysis is to determine whether the abnormalities in the subsequent stages are caused by the abnormalities in a previous specific stage, and whether these abnormalities show regular changes. If an abnormality occurs in a process stage, and the abnormalities in the subsequent stages can be attributed to this initial abnormal stage, and the abnormal data of these subsequent stages show regular attenuation, that is, the degree of abnormality gradually decreases, then the system terminal determines that these subsequent abnormalities are attenuation abnormalities caused by the initial abnormal stage. However, if other abnormal processes are found in addition to the attenuation abnormality when performing the abnormal attenuation analysis, this means that there may be multiple independent abnormal sources, or the impact of the initial abnormal stage is not unique. Afterwards, the system terminal generates abnormal reminder information for the target abnormal stage determined by the abnormal attenuation analysis. These reminders include the specific location of the abnormal stage, the type of abnormality, the degree of abnormality, and possible causes, so that operators can quickly understand and deal with these abnormalities to ensure the stability and efficiency of the entire sewage treatment process. In this way, the sewage treatment process can be effectively monitored and managed to ensure the treatment quality of pollutants and environmental safety.

[0045] Further, the present application provides locating an initial abnormal phase sequence based on the multi-phase verification result, and performing abnormal attenuation analysis on the abnormal phase sequence to locate the target abnormal phase, and the method also includes:

[0046] Traversing the plurality of continuous sewage treatment stages, performing continuous attenuation identification of common characteristics of single stage anomalies, and obtaining a single stage common characteristic attenuation relationship;

[0047] Based on the single-stage common characteristic attenuation relationship, the abnormal attenuation stage of the state monitoring sequence data of the abnormal stage sequence is identified to obtain the target abnormal stage.

[0048] Preferably, when dealing with a multi-stage sewage treatment process, in order to ensure the stability and efficiency of the entire treatment process, the system terminal accurately identifies and locates possible anomalies. A key step is to traverse all continuous sewage treatment stages and identify the continuous attenuation of common features of single-stage anomalies. Specifically, the system terminal analyzes the state monitoring data for each sewage treatment stage to identify whether there are abnormal features. These abnormal features may be manifested as a sudden increase in pollutant concentration, abnormal flow fluctuations, etc. If abnormal features are found in a certain stage, the specific manifestations and data points of these features are recorded. Subsequently, for the identified abnormal stage, the state monitoring data of its subsequent stages are analyzed to observe whether there are features similar to the abnormal stage and whether these features show a trend of continuous attenuation. The continuous attenuation of common features is manifested as the gradual weakening of abnormal features in subsequent stages, for example, the pollutant concentration gradually decreases, the flow fluctuation gradually decreases, etc. If it is found that there are features similar to the abnormal stage in the subsequent stage, and these features show a trend of continuous attenuation, then the system terminal determines that these features are common features caused by the abnormal stage. Continuous attenuation. Afterwards, based on the analysis of the abnormal stage and its subsequent stages, the attenuation relationship of the common features of a single stage is determined. This relationship describes the pattern and law of the attenuation of common characteristics between the abnormal stage and the subsequent stage. The attenuation relationship includes key parameters such as the attenuation rate, attenuation duration, and attenuation amplitude.

[0049] After obtaining the common feature attenuation relationship of a single stage, the system terminal uses this information to further analyze the state monitoring sequence data of the abnormal stage sequence. By performing attenuation consistency verification of adjacent stages of these attenuation relationships of the abnormal stage sequence, it is possible to determine whether the abnormal stage presents a pattern consistent with the attenuation of the common features. If the verification passes, the system terminal adds the abnormal stage to the target abnormal stage. This target abnormal stage is the initial abnormal stage that causes the common feature attenuation in subsequent stages. By accurately identifying this target abnormal stage, more targeted problem investigation and processing can be carried out to ensure the normal operation of the entire sewage treatment process.

[0050] Further, the present application provides for performing abnormal attenuation phase identification on the state monitoring sequence data of the abnormal phase sequence based on the single phase common characteristic attenuation relationship to obtain the target abnormal phase, and the method further includes:

[0051] Extracting common features from the state monitoring sequence data of the abnormal phase sequence to obtain a common feature sequence;

[0052] Taking the first abnormal stage in the abnormal stage sequence as the starting point, an attenuation consistency check of adjacent stages is performed on the common feature sequence and the attenuation relationship of the common features of the single stage. When the attenuation consistency check of adjacent stages passes, the first abnormal stage is added to the target abnormal stage.

[0053] Optionally, in the process of multi-stage sewage treatment, when the abnormal stage sequence is generated, in order to more accurately locate the target abnormal stage, the system terminal analyzes the state monitoring data of the abnormal stage. First, extract the common features in the state monitoring sequence data of the abnormal stage sequence, which are manifested as abnormal patterns of pollutant concentration, flow or other key indicators. By extracting these common features, a common feature sequence can be obtained, which describes the features commonly presented in the abnormal stage. Subsequently, taking the first abnormal stage in the abnormal stage sequence as the starting point, its common features are compared with the attenuation relationship of the common features of a single stage. Check whether the common features of the subsequent adjacent stages also conform to this attenuation relationship. That is, check whether these features are consistent with the expected attenuation relationship in terms of numerical values, change trends, etc. If the common features of the adjacent stages all conform to the attenuation relationship, continue to verify the next adjacent stage; if not, stop the verification and add the first abnormal stage to the target abnormal stage, and then re-verify. If the common features of all adjacent stages from the first abnormal stage have passed the attenuation consistency check, the system terminal determines that the first abnormal stage is the target abnormal stage that causes the abnormality of the subsequent stage. Once the first abnormal stage is confirmed as the target abnormal stage, the system terminal adds the first abnormal stage to the list of target abnormal stages. In this way, the root abnormal stage that causes the entire abnormal stage sequence, i.e., the target abnormal stage, can be gradually identified. This helps to locate the problem more accurately, so that more effective measures can be taken to solve the problem and ensure the stability and efficiency of the sewage treatment process.

[0054] Furthermore, the present application provides that when any adjacent stage attenuation consistency check fails, the method further includes:

[0055] When the attenuation consistency check of any adjacent stage fails, the first abnormal stage is added to the target abnormal stage, and the second abnormal stage that fails the attenuation consistency check is initialized as the starting point, and the attenuation consistency check of the adjacent stages is repeated until the abnormal stage sequence is traversed, and all starting points that fail the attenuation consistency check are added to the target abnormal stage.

[0056] Optionally, if a situation that does not conform to the attenuation relationship is found in the verification of any adjacent stage, the system terminal stops the subsequent verification, and regards the first abnormal stage as a potential target abnormal stage and adds it to the target abnormal stage list. Subsequently, the system terminal takes the second abnormal stage as a new starting point, that is, the adjacent stage after the first abnormal stage, and continues to perform the attenuation consistency check. This is done to find other stages that may cause abnormal propagation. The system terminal repeats this process and continuously performs verification until the entire abnormal stage sequence is traversed. During the traversal process, each time the attenuation consistency check fails, the system terminal will take the adjacent and subsequent stage as the starting point and add the current stage to the target abnormal stage list to ensure that no potential stage that may cause abnormal propagation is missed. In this way, a list of all possible target abnormal stages can be constructed. These stages have been verified and determined to be the cause of abnormalities in subsequent stages. This list provides important information for the system terminal, helping the system terminal to more accurately understand and handle abnormal situations in the sewage treatment process.

[0057] Furthermore, the present application provides a method for generating abnormality reminder information of a sewage channel, and the method further includes:

[0058] Obtaining pollutant flow channels of the plurality of consecutive sewage treatment stages;

[0059] Collecting channel flow monitoring information of the pollutant flow channel;

[0060] Preferably, in the process of treating continuous sewage treatment, in order to effectively monitor and manage the circulation of pollutants, the system terminal obtains the pollutant circulation channels between these stages. These channels are the paths for pollutants to flow from one treatment stage to the next, and are an important part of sewage treatment. After determining the pollutant circulation channels, the system terminal collects the flow monitoring information of these channels. This is done through flow monitoring devices installed on the channels, which can record and transmit the flow data in the channels in real time. These data are crucial for understanding the circulation of pollutants, evaluating treatment effects, and discovering potential problems. In summary, by obtaining pollutant circulation channels and collecting channel flow monitoring information, the entire sewage treatment process can be more comprehensively monitored and managed. This helps to promptly discover and solve potential pollution problems and ensure the normal operation of the sewage treatment system.

[0061] Identify channel blocking indicators based on the channel flow monitoring information;

[0062] When the channel blocking index is greater than a preset index, a sewage channel abnormality reminder message is generated.

[0063] Preferably, when treating sewage, in order to ensure the smooth flow of pollutants, the system terminal monitors the flow of the pollutant flow channel. Based on these channel flow monitoring information, the channel blocking index is identified. Specifically, the real-time flow data is compared with the normal flow range. If the real-time flow is within the normal range, the channel is in a normal state; if the real-time flow is lower than the lower limit of the normal range, there is a channel blocking situation. Subsequently, the system terminal uses the lower limit of the normal flow range to subtract the real-time flow, and performs a ratio operation with the lower limit of the normal flow range. If the calculation result is a positive value, it means that there may be a blockage in the pollutant flow channel, and the calculation result is used as the channel blocking index. On the contrary, it means that there is no blockage in the pollutant flow channel, and the channel blocking index is set to 0. After that, the system terminal compares the calculated channel blocking index with the preset index. If the channel blocking index is greater than the preset index, it means that there is a blockage in the pollutant flow channel. The system terminal will automatically generate abnormal reminder information for the sewage channel. This reminder information includes information such as the specific location of the channel, the degree of blockage, possible causes, and recommended countermeasures, so that relevant personnel can take timely action to solve the channel blocking problem and ensure the normal progress of sewage treatment and the effective treatment of pollutants.

[0064] In summary, the embodiments of the present application have at least the following technical effects:

[0065] The embodiment of the present application obtains information on multiple continuous sewage treatment stages for treating the first pollutant on the target ship. Subsequently, by collecting pollutant treatment samples under a preset time zone, a multi-stage sewage analysis model is trained, which can generate multi-stage treatment parameters and predicted treatment quality parameters based on the state information of the initial pollutant. Using these parameters, the first sewage discharge equipment is controlled, and the state monitoring data of multiple continuous sewage treatment stages are collected in real time. After that, by comparing the actual state monitoring data with the predicted treatment quality parameters, a stage alignment check is performed, and the initial abnormal stage sequence is located based on the check result. In order to further determine the specific location of the abnormality, an abnormal attenuation analysis is performed on the abnormal stage sequence, the target abnormal stage is located, and corresponding abnormal reminder information is generated. In addition, it also includes monitoring of the pollutant circulation channel, by collecting channel flow monitoring information, identifying channel blocking indicators, and generating sewage channel abnormal reminder information when the indicator exceeds the preset value. These technical effects jointly solve the technical problems that multiple continuous treatment stages are difficult to effectively monitor and abnormalities are difficult to locate during ship sewage discharge, and realize intelligent and automated sewage discharge monitoring, and improve the efficiency and accuracy of sewage treatment.

[0066] Embodiment 2

[0067] Based on the same inventive concept as the intelligent ship sewage discharge monitoring method in the above-mentioned embodiment, Figure 2As shown, the present application provides an intelligent marine sewage discharge monitoring system, the system comprising:

[0068] Processing stage acquisition module 1: the processing stage acquisition module 1 is used to acquire a plurality of continuous sewage treatment stages for treating a first pollutant on a target ship;

[0069] Model training module 2: the model training module 2 is used to collect pollutant treatment samples of the multiple continuous sewage treatment stages in a preset time zone and train a multi-stage sewage analysis model;

[0070] Processing and analysis module 3: the processing and analysis module 3 is used to collect the pollutant state information of the initial pollutants received in the initial processing stage and input it into the multi-stage pollution analysis model to perform pollution treatment analysis, and generate multi-stage processing parameters and multi-stage predicted processing quality parameters;

[0071] Equipment control module 4: the equipment control module 4 is used to generate a control signal with the multi-stage processing parameters, control the first sewage discharge equipment of the first pollutant, and collect multi-stage status monitoring data under the multiple continuous sewage treatment stages;

[0072] Alignment verification module 5: the alignment verification module 5 is used to perform stage alignment verification on the multi-stage state monitoring data and the multi-stage prediction processing quality parameters to generate a multi-stage verification result;

[0073] Attenuation analysis module 6: The attenuation analysis module 6 is used to locate the initial abnormal stage sequence based on the multi-stage verification result, and perform abnormal attenuation analysis on the initial abnormal stage sequence, locate the target abnormal stage, and generate abnormal reminder information for the target abnormal stage.

[0074] Furthermore, the model training module 2 is also used to perform the following method:

[0075] The preset time zone includes time intervals under multiple equipment maintenance nodes, the pollutant treatment samples include multiple treatment samples under multiple equipment maintenance nodes, and any treatment sample includes an initial pollutant state sample, a multi-stage treatment parameter sample, and a multi-stage predicted quality sample;

[0076] Extracting the first processed sample under the equipment maintenance node closest to the current moment, and training and constructing the multi-stage sewage analysis model;

[0077] Using the multiple processing samples under the multiple equipment maintenance nodes to identify the performance degradation of the pollutant treatment equipment, and using the Markov chain to construct a multi-stage performance degradation feedback network;

[0078] The multi-stage performance attenuation feedback network is connected to the multi-stage pollution emission analysis model, and feedback optimization is performed on the output of the multi-stage pollution emission analysis model.

[0079] Furthermore, the model training module 2 is also used to perform the following method:

[0080] Based on the multiple processing samples, the first-stage processing parameter sequence, the second-stage processing parameter sequence, and the N-th-stage processing parameter sequence under the multiple equipment maintenance nodes are extracted with the pollutant states of the adjacent previous stage being consistent as the first constraint condition and the stage control target being consistent as the second constraint condition, wherein N is the total number of stages of the multiple continuous sewage treatment stages;

[0081] Performing processing parameter error calculations at adjacent nodes on the first-stage processing parameter sequence, the second-stage processing parameter sequence, and up to the N-stage processing parameter sequence, respectively, to obtain a first error sequence, a second error sequence, and up to the N-th error sequence;

[0082] Based on the Markov chain, the multi-stage performance decay feedback network is constructed according to the first error sequence, the second error sequence, and up to the Nth error sequence.

[0083] Furthermore, the attenuation analysis module 6 is also used to perform the following method:

[0084] Traversing the plurality of continuous sewage treatment stages, performing continuous attenuation identification of common characteristics of single stage anomalies, and obtaining a single stage common characteristic attenuation relationship;

[0085] Based on the single-stage common characteristic attenuation relationship, the abnormal attenuation stage of the state monitoring sequence data of the abnormal stage sequence is identified to obtain the target abnormal stage.

[0086] Furthermore, the attenuation analysis module 6 is also used to perform the following method:

[0087] Extracting common features from the state monitoring sequence data of the abnormal phase sequence to obtain a common feature sequence;

[0088] Taking the first abnormal stage in the abnormal stage sequence as the starting point, an attenuation consistency check of adjacent stages is performed on the common feature sequence and the attenuation relationship of the common features of the single stage. When the attenuation consistency check of adjacent stages passes, the first abnormal stage is added to the target abnormal stage.

[0089] Furthermore, the attenuation analysis module 6 is also used to perform the following method:

[0090] When the attenuation consistency check of any adjacent stage fails, the first abnormal stage is added to the target abnormal stage, and the second abnormal stage that fails the attenuation consistency check is initialized as the starting point, and the attenuation consistency check of the adjacent stages is repeated until the abnormal stage sequence is traversed, and all starting points that fail the attenuation consistency check are added to the target abnormal stage.

[0091] Furthermore, the attenuation analysis module 6 is also used to perform the following method:

[0092] Obtaining pollutant flow channels of the plurality of consecutive sewage treatment stages;

[0093] Collecting channel flow monitoring information of the pollutant flow channel;

[0094] Identify channel blocking indicators based on the channel flow monitoring information;

[0095] When the channel blocking index is greater than a preset index, a sewage channel abnormality reminder message is generated.

[0096] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0097] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0098] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An intelligent marine sewage discharge monitoring method, characterized in that: The method comprises: Obtaining a plurality of consecutive blowdown treatment stages for treating a first pollutant on a target vessel; Collect pollutant treatment samples of the multiple continuous sewage treatment stages in a preset time zone, and train a multi-stage sewage analysis model; Collecting pollutant state information of initial pollutants received in the initial treatment stage and inputting it into the multi-stage pollutant analysis model to perform pollutant treatment analysis, and generate multi-stage treatment parameters and multi-stage predicted treatment quality parameters; generating a control signal with the multi-stage treatment parameters, controlling a first sewage discharge device for the first pollutant, and collecting multi-stage status monitoring data in the plurality of continuous sewage treatment stages; Performing a stage alignment check on the multi-stage state monitoring data and the multi-stage prediction processing quality parameters to generate a multi-stage check result; Based on the multi-stage verification result, the initial abnormal stage sequence is located, and abnormal attenuation analysis is performed on the initial abnormal stage sequence to locate the target abnormal stage, and abnormal reminder information is generated for the target abnormal stage; based on the multi-stage verification result, the initial abnormal stage sequence is located, and abnormal attenuation analysis is performed on the initial abnormal stage sequence to locate the target abnormal stage, including: Traversing the plurality of continuous sewage treatment stages, performing continuous attenuation identification of common characteristics of single stage anomalies, and obtaining a single stage common characteristic attenuation relationship; Based on the single-stage common characteristic attenuation relationship, the state monitoring sequence data of the initial abnormal stage sequence is subjected to abnormal attenuation stage identification to obtain the target abnormal stage; The target abnormal stage is an initial abnormal stage that causes common feature attenuation in subsequent multiple stages.

2. The method according to claim 1, characterized in that Collect pollutant treatment samples of the multiple continuous sewage treatment stages in the preset time zone, and train a multi-stage sewage analysis model, including: The preset time zone includes time intervals under multiple equipment maintenance nodes, the pollutant treatment samples include multiple treatment samples under multiple equipment maintenance nodes, and any treatment sample includes an initial pollutant state sample, a multi-stage treatment parameter sample, and a multi-stage predicted quality sample; Extracting the first processed sample under the equipment maintenance node closest to the current moment, and training and constructing the multi-stage sewage analysis model; Using the multiple processing samples under the multiple equipment maintenance nodes to identify the performance degradation of the pollutant treatment equipment, and using the Markov chain to construct a multi-stage performance degradation feedback network; The multi-stage performance attenuation feedback network is connected to the multi-stage pollution emission analysis model, and feedback optimization is performed on the output of the multi-stage pollution emission analysis model.

3. The method according to claim 2, characterized in that The performance degradation of the pollutant treatment equipment is identified by using the multiple processing samples under the multiple equipment maintenance nodes, and a multi-stage performance degradation feedback network is constructed by using a Markov chain, including: Based on the multiple processing samples, the first constraint condition is that the pollutant state of the adjacent previous stage is consistent, and the second constraint condition is that the stage control target is consistent, extracting the first stage processing parameter sequence, the second stage processing parameter sequence, and the Nth stage processing parameter sequence under the multiple equipment maintenance nodes, wherein N is the total number of stages of the multiple continuous sewage treatment stages; Performing processing parameter error calculations at adjacent nodes on the first-stage processing parameter sequence, the second-stage processing parameter sequence, and up to the N-stage processing parameter sequence, respectively, to obtain a first error sequence, a second error sequence, and up to the N-th error sequence; Based on the Markov chain, the multi-stage performance decay feedback network is constructed according to the first error sequence, the second error sequence, and up to the Nth error sequence.

4. The method according to claim 1, characterized in that Based on the single-stage common characteristic attenuation relationship, the state monitoring sequence data of the initial abnormal stage sequence is subjected to abnormal attenuation stage identification to obtain the target abnormal stage, including: Extracting common features from the state monitoring sequence data of the initial abnormal phase sequence to obtain a common feature sequence; Taking the first abnormal stage in the initial abnormal stage sequence as the starting point, an attenuation consistency check of adjacent stages is performed on the common feature sequence and the attenuation relationship of the common features of the single stage. When the attenuation consistency check of adjacent stages passes, the first abnormal stage is added to the target abnormal stage.

5. The method according to claim 4, characterized in that When the attenuation consistency check of any adjacent stage fails, the first abnormal stage is added to the target abnormal stage, and the second abnormal stage that fails the attenuation consistency check is initialized as the starting point, and the attenuation consistency check of the adjacent stages is repeated until the initial abnormal stage sequence is traversed, and all starting points that fail the attenuation consistency check are added to the target abnormal stage.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining pollutant flow channels of the plurality of consecutive sewage treatment stages; Collecting channel flow monitoring information of the pollutant flow channel; Identify channel blocking indicators based on the channel flow monitoring information; When the channel blocking index is greater than a preset index, a sewage channel abnormality reminder message is generated.

7. An intelligent marine sewage monitoring system, characterized in that: The steps for implementing an intelligent ship sewage discharge monitoring method as described in any one of claims 1 to 6 include: A treatment stage acquisition module: acquiring a plurality of continuous sewage treatment stages for treating a first pollutant on a target ship; Model training module: collecting pollutant treatment samples of the multiple continuous sewage treatment stages in a preset time zone, and training a multi-stage sewage analysis model; Processing and analysis module: collecting pollutant status information of initial pollutants received in the initial processing stage and inputting it into the multi-stage pollutant analysis model to perform pollutant treatment analysis, and generate multi-stage processing parameters and multi-stage predicted processing quality parameters; Equipment control module: generating a control signal with the multi-stage processing parameters, controlling the first sewage discharge equipment of the first pollutant, and collecting multi-stage status monitoring data in the multiple continuous sewage treatment stages; Alignment verification module: performing stage alignment verification on the multi-stage state monitoring data and the multi-stage prediction processing quality parameters to generate a multi-stage verification result; Attenuation analysis module: locates the initial abnormal stage sequence based on the multi-stage verification result, performs abnormal attenuation analysis on the initial abnormal stage sequence, locates the target abnormal stage, and generates abnormal reminder information for the target abnormal stage.

Images