Monitoring method of fish concentrated transportation control system

Abstract

The invention provides a monitoring method of a fish concentrated transportation control system, and relates to the technical field of water conservancy and hydropower. The method comprises the following steps: acquiring real-time monitoring data of a fish concentrated transportation control system; a pre-trained exception recognition model is adopted to perform exception recognition on the real-time monitoring data, a target exception mode of the fish concentrated transportation control system is obtained, and the target exception mode is used for indicating that target equipment in the fish concentrated transportation control system has a target fault problem; and triggering an exception handling program for executing the target exception mode to repair the target exception mode to obtain a repair result of the target exception mode. By adopting the method provided by the invention, the fault target equipment in the fish concentrated transportation control system can be automatically repaired, the efficiency is high, and the human resource investment is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of water conservancy and hydropower, and in particular to a monitoring method for a fish collection and transportation control system. Background Art

[0002] The fish collection and transportation system of a hydropower station is a system based on Internet of Things technology that is used to monitor, manage and transport fish resources in a hydropower station. In the fish collection and transportation system of a hydropower station, it is usually necessary to use an automated control system to control the operation of equipment (such as fish lifts and fish transport vehicles).

[0003] When an abnormal problem occurs in an automated control system, it is necessary to repair the abnormal problem. However, currently the repair of problems in automated control systems relies on manual maintenance by professionals, which is inefficient and consumes a lot of human resources. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present application provides a monitoring method for a fish transport control system so as to solve the problems existing in the prior art.

[0005] The technical solution adopted in the embodiment of the present application is as follows:

[0006] In a first aspect, an embodiment of the present application provides a monitoring method for a fish transport control system, comprising:

[0007] Obtain real-time monitoring data of the fish transport control system;

[0008] Using a pre-trained anomaly recognition model, the real-time monitoring data is subjected to anomaly recognition to obtain a target anomaly mode of the fish transport control system, wherein the target anomaly mode is used to indicate that a target device in the fish transport control system has a target fault problem;

[0009] The exception handling program of the target exception mode is triggered to perform repair on the target exception mode, and a repair result of the target exception mode is obtained.

[0010] In a second aspect, the embodiment of the present application further provides a monitoring device for a fish transport control system, including:

[0011] An acquisition module is used to acquire real-time monitoring data of the fish transport control system;

[0012] an identification module, used to use a pre-trained abnormality identification model to perform abnormality identification on the real-time monitoring data, and obtain a target abnormality mode of the fish transport control system, wherein the target abnormality mode is used to indicate that a target device in the fish transport control system has a target fault problem;

[0013] The repair module is used to trigger the execution of the exception handling program of the target exception mode to repair the target exception mode and obtain the repair result of the target exception mode.

[0014] In a third aspect, the present application provides a computer device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor and the storage medium communicate via the bus, and the processor executes the program instructions to implement the monitoring method of the fish transport control system described in any of the above embodiments.

[0015] In a fourth aspect, the present application provides a readable storage medium having program instructions stored thereon, and the program instructions, when executed by a processor, implement the monitoring method of the fish transport control system described in any of the above embodiments.

[0016] The beneficial effects of the present application are as follows: the present application provides a monitoring method for a fish transport control system, comprising: obtaining real-time monitoring data of the fish transport control system; using a pre-trained abnormality recognition model to perform abnormality recognition on the real-time monitoring data, and obtaining a target abnormality mode of the fish transport control system, wherein the target abnormality mode is used to indicate that a target device in the fish transport control system has a target fault problem; triggering an abnormality handling program for executing the target abnormality mode to repair the target abnormality mode and obtaining a repair result of the target abnormality mode.

[0017] Among them, the target abnormal pattern is obtained according to the abnormality recognition model, and then the target abnormal pattern is repaired according to the abnormality handling procedure, which realizes the automatic repair of the faulty target equipment in the fish transport control system, with high efficiency and reduced human resource investment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 One of the flow charts of the monitoring method of the fish transport control system provided in one embodiment of the present application;

[0020] Figure 2 A second flow chart of a monitoring method for a fish transport control system provided in an embodiment of the present application;

[0021] Figure 3A third flow chart of a monitoring method for a fish transport control system provided in an embodiment of the present application;

[0022] Figure 4 A fourth flow chart of a monitoring method for a fish transport control system provided in an embodiment of the present application;

[0023] Figure 5 A fifth flow chart of a monitoring method for a fish transport control system provided in an embodiment of the present application;

[0024] Figure 6 A sixth flow chart of a monitoring method for a fish transport control system provided in an embodiment of the present application;

[0025] Figure 7 Flow chart 7 of the monitoring method of the fish transport control system provided in one embodiment of the present application;

[0026] Figure 8 FIG8 is a flow chart of a monitoring method for a fish transport control system provided in an embodiment of the present application;

[0027] Fig. 9 A ninth flowchart of a monitoring method for a fish transport control system provided in an embodiment of the present application;

[0028] Fig.10 A schematic diagram of the structure of a monitoring device for a fish transport control system provided in an embodiment of the present application;

[0029] Fig.11 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0031] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0032] In addition, the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] It should be noted that, in the absence of conflict, the features in the embodiments of the present application may be combined with each other.

[0034] An embodiment of the present application provides a monitoring method for a fish transport control system, which can be generated by any computer device with computing and processing capabilities. The computer device can be, for example, a terminal-oriented computer device or a back-end server.

[0035] The following is a specific example description of the monitoring method of the fish transport control system provided by the present application through multiple examples in combination with the accompanying drawings.

[0036] Figure 1 One of the flow charts of the monitoring method of the fish transport control system provided in one embodiment of the present application is as follows: Figure 1 As shown, the method includes:

[0037] S101, obtaining real-time monitoring data of the fish transport control system.

[0038] The fish collection and transportation control system is a system based on the Internet of Things technology, which is used to monitor, manage and transport fish resources in hydropower stations. The fish collection and transportation control system, which consists of sensors, data collectors, cloud platforms and mobile terminals, is one of the important fish protection projects in hydropower stations. Its function is to transport the collected fish under the dam and release them to the appropriate release site.

[0039] The real-time monitoring data of the fish transport control system is data that can reflect the operating status of the fish transport control system, including but not limited to sensor readings, the operating status of the fish transport control system, the operation log of the fish transport control system, etc., and the real-time monitoring data includes data under normal operation and various known error states.

[0040] For example, sensor readings may include tension sensor data, including tension sensor readings recorded during the operation of various water discharge gates and equipment; position sensor data, including position sensor data of equipment such as fish driving screens and fish hoists, which are used to track the specific position of the equipment; collision limit switch data is used to record the state of the equipment reaching the collision limit switch, indicating whether the equipment has reached the limit position.

[0041] The operating status may include hydrological data, including water flow velocity, which is used to record the water flow velocity and evaluate the impact of hydrological conditions on equipment operation; water replenishment level, which is used to record the water level height and reflect the water level changes; water temperature data, which is used to record the water temperature and evaluate the impact of water temperature on system operation; fish transport vehicle data, including location data, which is used to record the current location of the fish transport vehicle and track the movement path of the fish transport vehicle; power data, which is used to record the power status of the fish transport vehicle and evaluate the impact of power on operation; operating mode, which is used to record the current operating mode of the system (such as normal mode, maintenance mode, fault mode, etc.); resource usage, including system resource data such as CPU usage and memory usage.

[0042] Operation logs include operation records, system startup, shutdown, restart and other operation logs. For example, user operation logs are used to record specific operations of users in the system (such as login, logout, permission change, etc.); system event logs include system exceptions, warnings, errors and other event logs; error status data logs include known error types, which are used to record different types of known errors and their occurrence time; error description logs are used to record detailed descriptions of errors and their impact range; system status logs when errors occur, which are used to record sensor readings and system status when errors occur; timestamps for each record are used to record the specific time of data collection to ensure the timeliness of data.

[0043] S102: Use a pre-trained anomaly recognition model to perform anomaly recognition on the real-time monitoring data to obtain a target anomaly mode of the fish transport control system.

[0044] The anomaly recognition model is a pre-trained model that can be used to identify anomalies in real-time monitoring data and obtain the target anomaly mode of the fish collection and transportation control system, wherein the target anomaly mode is used to indicate that a target device in the fish collection and transportation control system has a target fault problem. The target device can be any device in the fish collection and transportation control system that has a fault problem, such as fish driving fences, fish lifting equipment, fish transport equipment, control equipment for each water release gate, and other equipment.

[0045] S103: triggering the execution of an exception handling program of a target exception mode to repair the target exception mode and obtain a repair result of the target exception mode.

[0046] After obtaining the target abnormal pattern, the exception handling program of the target abnormal pattern is triggered to repair the target abnormal pattern and obtain the repair result of the target abnormal pattern. Among them, the exception handling program can be triggered by a decision system integrated with preset fuzzy control logic, including but not limited to a complex event processing system (Complex Event Processing, CEP), which can be used to analyze event streams in real time and trigger corresponding exception handling programs.

[0047] In summary, this embodiment provides a monitoring method for a fish transport control system, which obtains a target abnormal pattern based on an abnormality recognition model, and then repairs the target abnormal pattern according to an abnormality handling procedure, thereby automatically repairing faulty target devices in the fish transport control system, with high efficiency and reduced human resource investment.

[0048] Optionally, after obtaining the repair result of the target abnormal pattern, the abnormality recognition model can also be updated according to the fault repair result of the target abnormal pattern, including but not limited to improving the self-diagnosis and self-repair capabilities of the system through artificial intelligence and big data analysis to ensure the stability of the system.

[0049] For example, you can develop automated repair scripts that automatically perform repair operations when a specific type of fault problem is detected; use reinforcement learning algorithms to train the system so that it can automatically adjust parameters and optimize performance when faced with new problems; build a knowledge base that contains historical fault cases, solutions, and best practices for reference by the anomaly recognition model system; and, based on the knowledge base, combine analysis results with knowledge base information to provide maintenance personnel with repair suggestions.

[0050] Adaptive mechanisms and robust designs can also be used to enable the anomaly recognition model to have continuous learning capabilities, and to improve the accuracy of diagnosis and repair by constantly learning from new data; online learning technology can be used to enable the anomaly recognition model to adapt to the ever-changing operating environment and needs; feedback mechanisms can also be designed to feed back the repair results and the performance of the anomaly recognition model to the AI ​​model for iterative improvement of the model; the effectiveness of the anomaly recognition model's self-diagnosis and self-repair can be regularly evaluated, and strategies and anomaly recognition models can be adjusted based on the evaluation results.

[0051] Among them, an automated repair script is developed to automatically perform repair operations when a specific type of fault problem is detected. The specific types of fault problems include hardware faults, software faults, and environmental factor faults. Specifically, hardware faults include sensor faults such as abnormal or lost sensor readings, sensor disconnection or short circuits; actuator (winches, power equipment, and related sensors) faults such as the inability of the actuator to respond to control commands, actuator position offset or misalignment, and actuator response time being too long; communication faults such as data transmission delays or interruptions, unstable network connections, or packet loss; power supply faults such as unstable voltage or power outages, and power module failures.

[0052] Software failures include program errors such as logical errors or bugs in the code, memory leaks or overflows; system crashes such as operating system or control software crashes, system restarts or freezes; incorrect or damaged data formats, database connection failures or query errors, etc.

[0053] Environmental failures include temperature abnormalities such as equipment overheating or overcooling, ambient temperature exceeding the equipment operating range, etc.; water level abnormalities such as water level being too high or too low, and water level sensor failure.

[0054] Figure 2 The second flow chart of the monitoring method of the fish transport control system provided in one embodiment of the present application is as follows: Figure 2 As shown, the triggering of executing the exception handling program of the target exception mode in S103 to repair the target exception mode includes:

[0055] S201. Obtain target monitoring data corresponding to a target fault problem related to a target device from real-time monitoring data.

[0056] The exception handling procedure that triggers the execution of the target exception mode first obtains the target monitoring data corresponding to the target fault problem related to the target device from the real-time monitoring data, that is, the target monitoring data is the monitoring data corresponding to the target device related to the target fault problem. In this embodiment, the target monitoring data is sensor data.

[0057] S202. Based on the target monitoring data, a decision system integrated with preset fuzzy control logic is used to generate fuzzy control instructions including multiple target decision instructions.

[0058] The decision-making system integrated with the preset fuzzy control logic may include, for example, but is not limited to, a complex event processing system (Complex Event Processing, CEP). The preset fuzzy control logic is integrated in the fuzzy logic controller, and the target monitoring data is input into the fuzzy logic controller to generate fuzzy control instructions including multiple target decision instructions. The fuzzy control instructions are used to indicate the processing method for the target abnormal mode.

[0059] S203: Execute the fuzzy control instruction to repair the target abnormal mode.

[0060] After obtaining the fuzzy control instruction, the fuzzy control instruction can be executed to repair the target abnormal mode.

[0061] In one embodiment, S202 generates a fuzzy control instruction including multiple target decision instructions using a decision system integrated with a preset fuzzy control logic according to the target monitoring data, including:

[0062] S301. Using preset fuzzy control logic, determine multiple fuzzy sets in which target monitoring data are located.

[0063] The preset fuzzy control logic is integrated in the fuzzy logic controller. The target monitoring data is input into the fuzzy logic controller, and the fuzzy logic controller can convert the input data into fuzzy sets according to the fuzzy logic rules to obtain multiple fuzzy sets where the target monitoring data is located. Among them, the fuzzy logic rules can be obtained based on historical data analysis or expert knowledge.

[0064] S302, using preset fuzzy control logic, performing logical operations according to multiple fuzzy sets, and generating fuzzy control instructions of multiple target decision instructions.

[0065] Logical operations are performed according to the multiple fuzzy sets in which the target monitoring data are located to generate fuzzy control instructions for multiple target decision instructions.

[0066] The following describes a method for repairing a target abnormal mode according to multiple embodiments.

[0067] In one embodiment, if the target abnormal mode is the first abnormal mode, the fuzzy control instruction is the first fuzzy control instruction corresponding to the first abnormal mode. The first abnormal mode is used to indicate that there is a resistance increase problem in the fish driving fence equipment in the fish collection and transportation control system.

[0068] In this case, the methods for repairing the target abnormal mode include at least the following three:

[0069] S401, executing a first decision instruction in the first fuzzy control instruction to push dredging warning indication information for a fishway corresponding to the fish driving fence device.

[0070] The first decision instruction is used to push dredging warning instruction information for the fishway corresponding to the fish-driving fence device, so as to prompt the staff to dredge the fishway corresponding to the fish-driving fence device as soon as possible.

[0071] S402, executing the second decision instruction in the first fuzzy control instruction to detect the water flow state information of the fishway corresponding to the fish driving fence device.

[0072] The second decision instruction is used to instruct the detection of water flow status information of the fishway corresponding to the fish driving fence device, and to confirm whether the resistance of the fish driving fence device increases due to abnormal water flow.

[0073] S403, executing the third decision instruction in the first fuzzy control instruction to reduce the fish-driving speed of the fish-driving fence device.

[0074] The third decision instruction is used to indicate the fish-driving speed of the fish-driving fence device, and to confirm whether the resistance of the fish-driving fence device increases due to the excessive fish-driving speed. If so, the fish-driving speed of the fish-driving fence device is reduced to restore the resistance of the fish-driving fence device to normal.

[0075] After executing the third decision instruction, the method for repairing the target abnormal mode may further include:

[0076] S501, obtaining new monitoring data of the fish transport control system after executing the third decision instruction.

[0077] After executing the third decision instruction, new monitoring data of the fish transport control system is obtained.

[0078] S502: Use an abnormality recognition model to perform abnormality recognition on new monitoring data to obtain abnormality recognition results of the fish transport control system.

[0079] The anomaly recognition model is used to identify anomalies in new monitoring data and obtain anomaly recognition results of the fish collection and transportation control system to determine whether the first abnormal mode, that is, the problem of increased resistance of the fish driving fence equipment, has been repaired.

[0080] S503. If the abnormal identification result indicates that the first abnormal mode has not been repaired, continue to execute the third decision instruction to control the fish-driving fence device to stop driving fish, and control the downstream equipment of the fish-driving fence device in the fish collection and transportation control system to stop running.

[0081] If the abnormal identification result indicates that the resistance of the fish-driving fence is still large, the third decision instruction is continued to be executed to control the fish-driving fence to stop driving fish, and control the downstream equipment of the fish-driving fence in the fish collection and transportation control system to stop running. Among them, the downstream equipment includes: fish lifting equipment, fish transportation equipment, etc. in the fish collection area.

[0082] In one embodiment, if the target abnormal mode is the second abnormal mode, the fuzzy control instruction is a second fuzzy control instruction corresponding to the second abnormal mode, wherein the second abnormal mode is used to indicate that there is a control failure problem in the valve corresponding to the fish collecting area of ​​the fish driving fence equipment in the fish collecting and transporting control system.

[0083] In this case, the methods for repairing the target abnormal mode include at least the following four:

[0084] S601, executing the first decision instruction in the second fuzzy control instruction to control the fish transport equipment in the fish transport control system to move away.

[0085] The first decision instruction is used to instruct the fish transport truck to leave immediately, and to confirm whether the valve control in the fish gathering area fails because the fish transport truck fails to leave in time and the fish are not transported away in time.

[0086] S602, executing the second decision instruction in the second fuzzy control instruction to control the fish lifting equipment corresponding to the fish gathering area to stop running.

[0087] The second decision instruction is used to instruct the fish lifting equipment to stop running and to confirm whether the valve control in the fish gathering area fails because the fish lifting equipment transports the fish to the valve but the fish are not transported away in time.

[0088] S603, executing the third decision instruction in the second fuzzy control instruction to stop the automatic start of the valve.

[0089] The third decision instruction is used to instruct the valve to stop self-starting and to confirm whether the valve is started frequently and the fish are not transported away in time, resulting in failure of valve control in the fish gathering area.

[0090] S604, executing the fourth decision instruction in the second fuzzy control instruction to output valve inspection warning information.

[0091] The fourth decision instruction is used to send valve inspection warning information to the staff, so that the staff can check the valve as soon as possible and confirm the cause of the valve error.

[0092] In one embodiment, the anomaly recognition model includes a decision tree model and a classification model, such as Figure 7 As shown, the method of using a pre-trained abnormality recognition model in S102 to perform abnormality recognition on real-time monitoring data to obtain a target abnormality mode of the fish transport control system may include:

[0093] S701. Use the decision tree model in the abnormality identification model to identify abnormalities in the real-time monitoring data and obtain the target device with faults in the fish transport control system.

[0094] By using the decision tree model in the anomaly identification model to identify anomalies in real-time monitoring data, the preliminary classification results of the faults can be obtained and the target equipment with faults in the fish transport control system can be determined.

[0095] S702: Obtain target monitoring data related to the target device from the real-time monitoring data.

[0096] After determining the target device with a fault, target monitoring data related to the target device is obtained from the real-time monitoring data, including the monitoring data of the target device itself and the monitoring data of other devices related to the operation of the target device.

[0097] Taking the target device as the valve in the fish gathering area as an example, the target monitoring data related to the target device includes the monitoring data of the valve in the fish gathering area, the monitoring data of the fish lifting equipment, the monitoring data of the fish transporting equipment, and the monitoring data of other devices related to the valve in the fish gathering area.

[0098] S703: Use the classification model in the anomaly recognition model to perform anomaly recognition on the target monitoring data to obtain a target anomaly pattern.

[0099] After obtaining the target monitoring data related to the target device, the classification model in the abnormality recognition model is used to identify the abnormality of the target monitoring data, and the target abnormality pattern can be obtained. The target abnormality pattern is used to indicate the fault problem of the target device. The classification model can be, for example, a support vector machine (SVM).

[0100] like Figure 8 As shown, the embodiment of the present application also provides a training method for an abnormality recognition model.

[0101] S801. Acquire historical operation data of the fish transport control system, where the historical operation data includes: historical monitoring data under multiple preset abnormal modes.

[0102] First, the historical operation data of the fish transport control system is obtained. The historical operation data includes historical monitoring data under multiple preset abnormal modes, wherein the historical monitoring data includes but is not limited to: historical sensor readings, historical operating status of the fish transport control system, historical operation logs of the fish transport control system, etc.

[0103] S802: Perform feature selection on the historical monitoring data under each preset abnormal mode to obtain the historical target data under each preset abnormal mode.

[0104] The historical monitoring data under the preset abnormal mode, that is, the historical monitoring data when an error occurs in the fish transport control system.

[0105] Perform feature selection on the historical monitoring data under each preset abnormal mode to obtain the historical target data under each preset abnormal mode, including: perform feature selection to determine abnormal sensor readings, operation sequence, system response timestamp, operation type (automatic operation or user participation operation), non-operating system time (such as system restart, shutdown, etc.), resource usage (such as: PLC response time, server CPU, GPU, memory occupancy), etc.

[0106] S803: Using historical target data under multiple preset abnormal modes, a preset initial decision tree model and an initial classification model are trained to obtain an abnormality recognition model.

[0107] After preprocessing the historical target data under multiple preset abnormal modes, the preprocessed data is input into the preset deep learning network, and the preset initial decision tree model and initial classification model are trained to obtain the abnormal recognition model.

[0108] Preprocessing includes: cleaning data, processing missing values ​​and outliers; encoding features, such as converting categorical variables into numerical data; standardizing or normalizing numerical features to eliminate the impact of different magnitudes.

[0109] The preprocessed data is input into the preset deep learning network, and the preset initial decision tree model and initial classification model are trained, including: using the three feature selection methods of information gain, gain rate and Gini impurity for cross-validation to evaluate their performance on specific data sets and select the most appropriate feature selection method.

[0110] The following is an explanation of cross validation: Assume that there is a data set containing 1000 data records, and use 5-fold rolling cross validation (K=5) to evaluate the model. First, divide the data set into 5 subsets in chronological order, each subset contains 200 records. Then train and validate, the first time: the training set is from time point 1 to time point 200, and the test set is from time point 201 to time point 300; the second time: the training set is from time point 101 to time point 300, and the test set is from time point 301 to time point 400. And so on, until all the data is used up.

[0111] Information gain, gain ratio, and Gini impurity are three commonly used methods for evaluating and selecting features. In order to verify and evaluate their performance on time series datasets, cross validation can be performed. The following are the specific steps and explanations:

[0112] Information Gain: Information gain is a method to measure the importance of a feature in a data set. It evaluates the importance of a feature by calculating the reduction in information entropy of the feature to the target variable.

[0113] Gain Ratio: Gain Ratio is an improvement on information gain. It eliminates the preference of information gain for the diversity of feature numbers by dividing information gain by the intrinsic information of the feature.

[0114] Gini Impurity: Gini Impurity is used for feature selection in decision tree algorithms. It measures the impurity of the dataset when selecting a feature for splitting. The lower the Gini Impurity, the higher the importance of the feature.

[0115] Specific steps:

[0116] 1. Prepare data: Collect time series data of the automation control system, including various sensor readings, hydrological data, system status, operation logs, etc.

[0117] Data preprocessing: cleaning data, handling missing values, standardizing or normalizing features.

[0118] 2. Time Series Split: Use the Time Series Split method for cross validation, keeping the time order. K = 5.

[0119] 3. Feature selection and model training: Perform operations separately for each feature selection method (information gain, gain rate, Gini impurity).

[0120] Optionally, after obtaining the decision tree model, the performance of the decision tree model can be evaluated using methods such as cross-validation, and the parameters of the decision tree, such as the depth of the tree, the minimum number of split samples, etc., can be adjusted to optimize the decision tree model.

[0121] like Fig. 9 As shown, the embodiment of the present application also provides a method for constructing a decision-making system.

[0122] S901. Obtain historical failure cases of the fish container transport control system, candidate solutions to the historical failure cases, and optimal repair solutions to the historical failure cases.

[0123] Obtain historical failure cases of the fish container control system, candidate solutions to historical failure cases, and the best repair solutions to historical failure cases, that is, determine the key variables of the system and the relationship between them, and establish a preliminary framework of fuzzy rules. Among them, historical failure cases of the fish container control system, candidate solutions to historical failure cases, and the best repair solutions to historical failure cases can be obtained based on historical data methods, expert knowledge, or experience definitions.

[0124] S902: Build a decision-making knowledge base for the fish transport control system based on historical failure cases, candidate solutions to historical failure cases, and optimal repair solutions to historical failure cases.

[0125] According to the historical fault cases, the candidate solutions of the historical fault cases and the best repair solutions of the historical fault cases, the decision knowledge base of the fish transport control system is constructed and the appropriate membership function is selected.

[0126] S903. According to the decision knowledge base, a decision system is constructed using preset fuzzy control logic.

[0127] Genetic algorithms are used to optimize the parameters of fuzzy control logic, including the shape and specification of membership functions, and simulations and verifications are performed to build a decision-making system.

[0128] Among them, simulation and verification include: testing the performance of the system in a simulation environment and verifying the adaptive ability and decision quality of the decision-making system.

[0129] In summary, the present application embodiment provides a monitoring method for a fish transport control system, which has the following advantages:

[0130] 1. The target abnormal pattern is obtained according to the abnormal recognition model, and then the target abnormal pattern is repaired according to the abnormal handling procedure, which realizes the automatic repair of the faulty target equipment in the fish transport control system, improves the system's self-diagnosis and self-repair capabilities, is highly efficient, and reduces human resource investment.

[0131] 2. Ability to update the anomaly recognition model based on the fault repair results of the target anomaly pattern, improve the system's self-diagnosis and self-repair capabilities, and enhance system security and stability.

[0132] Optionally, when executing the method of any of the above embodiments of the present application, data can also be encrypted based on the Advanced Encryption Standard (AES) to ensure security during data transmission, and TLS / SSL protocol can be used for secure data communication to prevent data from being intercepted or tampered with during transmission.

[0133] The following is a corresponding explanation of the device, equipment and storage medium for executing the monitoring method of the fish transport control system provided by any of the above embodiments of the present application. Its specific implementation process and the technical effects produced are the same as those of the corresponding method embodiments mentioned above. For the sake of brief description, for the parts not mentioned in the following embodiments, please refer to the corresponding contents in the method embodiments.

[0134] Fig.10 A schematic diagram of the structure of a monitoring device for a fish transport control system provided in an embodiment of the present application, as shown in FIG. Fig.10 As shown, the device comprises:

[0135] The acquisition module 10 is used to acquire the real-time monitoring data of the fish transport control system.

[0136] The identification module 20 is used to use a pre-trained abnormality identification model to perform abnormality identification on the real-time monitoring data to obtain a target abnormality mode of the fish transport control system. The target abnormality mode is used to indicate that a target fault problem exists in a target device in the fish transport control system.

[0137] The repair module 30 is used to trigger the execution of the exception handling program of the target exception mode to repair the target exception mode and obtain the repair result of the target exception mode.

[0138] Optionally, the repair module 30 is used to obtain target monitoring data corresponding to the target fault problem related to the target equipment from the real-time monitoring data; based on the target monitoring data, a decision system integrated with preset fuzzy control logic is used to generate fuzzy control instructions including multiple target decision instructions; and the fuzzy control instructions are executed to repair the target abnormal mode.

[0139] Optionally, the repair module 30 is used to use a preset fuzzy control logic to determine the multiple fuzzy sets in which the target monitoring data is located; use the preset fuzzy control logic to perform logical operations based on the multiple fuzzy sets to generate fuzzy control instructions for multiple target decision instructions.

[0140] Optionally, the repair module 30 is used to execute a first decision instruction in the first fuzzy control instruction to push dredging warning indication information for the fishway corresponding to the fish driving fence device; execute a second decision instruction in the first fuzzy control instruction to detect water flow state information of the fishway corresponding to the fish driving fence device; execute a third decision instruction in the first fuzzy control instruction to reduce the fish driving speed of the fish driving fence device.

[0141] Optionally, the repair module 30 is used to obtain new monitoring data of the fish transport control system after executing the third decision instruction; use the abnormality recognition model to perform abnormality recognition on the new monitoring data to obtain an abnormality recognition result of the fish transport control system; if the abnormality recognition result indicates that the first abnormal mode has not been repaired, continue to execute the third decision instruction to control the fish driving fence equipment to stop driving fish, and control the downstream equipment of the fish driving fence equipment in the fish transport control system to stop running.

[0142] Optionally, the repair module 30 is used to execute the first decision instruction in the second fuzzy control instruction to control the fish transport equipment in the fish collection and transportation control system to move away; execute the second decision instruction in the second fuzzy control instruction to control the fish lifting equipment corresponding to the fish collection area to stop running; execute the third decision instruction in the second fuzzy control instruction to stop the automatic start of the valve; execute the fourth decision instruction in the second fuzzy control instruction to output the inspection warning information of the valve.

[0143] Optionally, the identification module 20 is used to use the decision tree model in the anomaly identification model to perform anomaly identification on the real-time monitoring data to obtain the target device with faults in the fish transport control system; obtain target monitoring data related to the target device from the real-time monitoring data; use the classification model in the anomaly identification model to perform anomaly identification on the target monitoring data to obtain the target anomaly pattern.

[0144] Optionally, the monitoring device of the fish transport control system also includes a training module for obtaining historical operating data of the fish transport control system, the historical operating data including: historical monitoring data under multiple preset abnormal modes; performing feature selection on the historical monitoring data under each preset abnormal mode to obtain historical target data under each preset abnormal mode; using the historical target data under multiple preset abnormal modes to train a preset initial decision tree model and an initial classification model to obtain an abnormal recognition model.

[0145] Optionally, the monitoring device of the fish transport control system further includes an updating module for updating the abnormality recognition model according to the fault repair result of the target abnormality pattern.

[0146] Optionally, a training module is used to obtain historical fault cases of the fish transport control system, candidate solutions to the historical fault cases, and optimal repair solutions to the historical fault cases; build a decision knowledge base of the fish transport control system based on the historical fault cases, candidate solutions to the historical fault cases, and optimal repair solutions to the historical fault cases; and build a decision system based on the decision knowledge base using preset fuzzy control logic.

[0147] The above-mentioned device is used to execute the method provided by the aforementioned embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0148] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), or one or more microprocessors, or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0149] like Fig.11 As shown, the present application provides a computer device, including: a processor 100, a storage medium 200 and a bus 300, the storage medium stores program instructions executable by the processor, when the computer device is running, the processor and the storage medium communicate through the bus, and the processor executes the program instructions to implement the monitoring method of the fish transport control system of any of the above embodiments.

[0150] Optionally, the present application provides a readable storage medium having program instructions stored thereon, and when the program instructions are executed by a processor, the monitoring method of the fish transport control system of any of the above embodiments is implemented.

[0151] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0152] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0153] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0154] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), disk or optical disk and other media that can store program codes.

[0155] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A monitoring method for a fish transport control system, characterized in that: include: Obtain real-time monitoring data of the fish transport control system; Using a pre-trained anomaly recognition model, the real-time monitoring data is subjected to anomaly recognition to obtain a target anomaly mode of the fish transport control system, wherein the target anomaly mode is used to indicate that a target device in the fish transport control system has a target fault problem; The exception handling program of the target exception mode is triggered to perform repair on the target exception mode, and a repair result of the target exception mode is obtained.

2. The method according to claim 1, characterized in that The triggering of executing the exception handling program of the target exception mode to repair the target exception mode includes: Acquire target monitoring data corresponding to the target fault problem related to the target device from the real-time monitoring data; According to the target monitoring data, a decision system integrated with preset fuzzy control logic is used to generate fuzzy control instructions including multiple target decision instructions; The fuzzy control instruction is executed to repair the target abnormal mode.

3. The method according to claim 2, characterized in that According to the target monitoring data, a decision system integrated with a preset fuzzy control logic is used to generate a fuzzy control instruction including a plurality of target decision instructions, including: Using the preset fuzzy control logic, determine the multiple fuzzy sets in which the target monitoring data is located; The preset fuzzy control logic is adopted to perform logical operations according to the multiple fuzzy sets to generate fuzzy control instructions for the multiple target decision instructions.

4. The method according to claim 2, characterized in that: The target abnormal mode is a first abnormal mode, and the first abnormal mode is used to indicate that there is a problem of increased resistance in the fish driving fence equipment in the fish collection and transportation control system; the fuzzy control instruction is a first fuzzy control instruction corresponding to the first abnormal mode; The executing the fuzzy control instruction to repair the target abnormal mode includes: Executing a first decision instruction in the first fuzzy control instruction to push dredging warning indication information for a fishway corresponding to the fish driving fence device; Executing a second decision instruction in the first fuzzy control instruction to detect water flow state information of the fishway corresponding to the fish driving fence device; The third decision instruction in the first fuzzy control instruction is executed to reduce the fish-driving speed of the fish-driving fence device.

5. The method according to claim 4, characterized in that The executing the fuzzy control instruction to repair the target abnormal mode also includes: Acquire new monitoring data of the fish transport control system after executing the third decision instruction; Using the abnormality recognition model, performing abnormality recognition on the new monitoring data to obtain an abnormality recognition result of the fish transport control system; If the abnormal identification result indicates that the first abnormal mode has not been repaired, continue to execute the third decision instruction to control the fish-driving fence device to stop driving fish, and control the downstream equipment of the fish-driving fence device in the fish collection and transportation control system to stop running.

6. The method according to claim 2, characterized in that The target abnormal mode is a second abnormal mode, and the second abnormal mode is used to indicate that there is a control failure problem in the valve of the fish collecting area corresponding to the fish driving fence device in the fish collecting and transporting control system; the fuzzy control instruction is a second fuzzy control instruction corresponding to the second abnormal mode; The executing the fuzzy control instruction to repair the target abnormal mode includes: Executing the first decision instruction in the second fuzzy control instruction to control the fish transport equipment in the fish transport control system to move away; Executing a second decision instruction in the second fuzzy control instruction to control the fish lifting equipment corresponding to the fish gathering area to stop running; executing a third decision instruction in the second fuzzy control instruction to stop the automatic start of the valve; Execute the fourth decision instruction in the second fuzzy control instruction to output inspection warning information of the valve.

7. The method according to claim 1, characterized in that The pre-trained abnormality recognition model is used to perform abnormality recognition on the real-time monitoring data to obtain the target abnormality mode of the fish transport control system, including: Using the decision tree model in the abnormality identification model, the real-time monitoring data is subjected to abnormality identification to obtain the target device where the fish transport control system has a fault; Acquire target monitoring data related to the target device from the real-time monitoring data; The classification model in the abnormality recognition model is used to perform abnormality recognition on the target monitoring data to obtain the target abnormality pattern.

8. The method according to claim 7, characterized in that Before the pre-trained abnormality recognition model is used to perform abnormality recognition on the real-time monitoring data to obtain the target abnormality mode of the fish transport control system, the method further includes: Acquiring historical operation data of the fish transport control system, wherein the historical operation data includes: historical monitoring data under a plurality of preset abnormal modes; Perform feature selection on the historical monitoring data under each preset abnormal mode to obtain the historical target data under each preset abnormal mode; The historical target data under the plurality of preset abnormal modes are used to train the preset initial decision tree model and the initial classification model to obtain the abnormality recognition model.

9. The method according to claim 1, characterized in that: The method further comprises: The abnormality recognition model is updated according to the fault repair result of the target abnormality mode.

10. The method according to claim 2, characterized in that Before generating the fuzzy control instructions including a plurality of target decision instructions by using a decision system integrated with a preset fuzzy control logic according to the target monitoring data, the method further comprises: Obtaining historical failure cases of the fish transport control system, candidate solutions to the historical failure cases, and optimal repair solutions to the historical failure cases; Constructing a decision knowledge base of the fish container transport control system according to the historical fault cases, the candidate solutions to the historical fault cases, and the best repair solutions to the historical fault cases; The decision system is constructed based on the decision knowledge base and using the preset fuzzy control logic.

Images