Hydraulic station remote flow control method and system based on Internet of Things

Abstract

The invention discloses a hydraulic station remote flow control method and system based on the Internet of Things, and relates to the technical field of remote flow control, and the hydraulic station remote flow control method based on the Internet of Things comprises the following steps: collecting operation data of a hydraulic station in real time by using a preset sensor group; analyzing the oil mass change of an oil reservoir in the hydraulic station based on the preprocessed operation data, and starting cross-regional oil mass appointment scheduling based on a prediction result of the oil mass change; establishing a dynamic balance model among the oil reservoir, the hydraulic pump and the control valve; the fault monitoring model is used for recognizing an oil mass conveying fault in the oil mass conveying process; and the oil mass conveying state among the oil storage device, the hydraulic pump and the control valve is adjusted according to the recognized oil mass conveying fault, so that remote control over the oil mass is achieved. According to the method, the oil reservoir, the hydraulic pump and the control valve are regarded as participants of the dynamic balance model, the oil mass conveying state among the participants can be effectively analyzed and coordinated, and coordinated operation of the system is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of remote flow control, and in particular to a method and system for remote flow control of a hydraulic station based on the Internet of Things. Background Art

[0002] The hydraulic station is a device that uses hydraulic technology to achieve liquid transmission, control and energy conversion. It is mainly composed of hydraulic pumps, oil reservoirs, control valves, actuators and other components. It is used to drive hydraulic equipment or perform hydraulic control tasks, and is essential to ensure the normal operation and performance of the hydraulic system. The hydraulic station draws liquid from the oil reservoir through the hydraulic pump, and then transports it to the hydraulic actuator or hydraulic system through the pipeline; the hydraulic pump is responsible for generating pressure and flow, pushing the liquid through the pipeline to the target position. At the same time, the control valve is used to adjust the flow direction, flow rate and flow of the liquid to achieve precise control of the system.

[0003] However, in the remote flow control of the hydraulic station, the dynamic balance between the hydraulic pump, the oil reservoir, and the control valve is crucial, and their interaction ensures the stable operation of the hydraulic system. The hydraulic pump provides pressure and power source to send liquid into the system; the oil reservoir stores liquid and balances the system pressure to ensure the smooth operation of the system; the control valve adjusts the flow and direction of the liquid according to demand and accurately controls the working state of the system. If the coordination between the three is unbalanced, the mismatch of flow and pressure will cause system pressure fluctuations, which will in turn affect the stability and reliability of the system.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the problems in the related art, the present invention proposes a hydraulic station remote flow control method and system based on the Internet of Things to overcome the above-mentioned technical problems existing in the existing related technology.

[0006] To this end, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a hydraulic station remote flow control method based on the Internet of Things is provided, and the hydraulic station remote flow control method based on the Internet of Things comprises the following steps: S1. Use the preset sensor group to collect the operating data of the hydraulic station in real time, and transmit the operating data to the Internet of Things platform for preprocessing; S2. Analyze the oil volume change of the oil reservoir in the hydraulic station based on the pre-processed operation data, and start cross-regional oil volume reservation scheduling based on the predicted results of the oil volume change; S3, establish a dynamic balance model between the oil reservoir, the hydraulic pump and the control valve, and evaluate the oil delivery status between the oil reservoir, the hydraulic pump and the control valve; S4, delivering the oil in the oil reservoir according to the oil delivery state, and identifying the oil delivery fault by using the fault monitoring model during the oil delivery process; S5. Adjust the oil delivery status between the oil reservoir, the hydraulic pump and the control valve according to the identified oil delivery fault to achieve remote control of the oil amount.

[0007] Preferably, the operation data of the hydraulic station includes oil reservoir data, hydraulic pump data and control valve data; The oil reservoir data includes the storage capacity of the oil reservoir, the oil reserve in the oil reservoir and the ambient temperature data of the oil reservoir; The hydraulic pump data includes the hydraulic pump's oil output per unit time, the hydraulic pump's output pressure, and the hydraulic pump's start and stop status; The control valve data includes the opening degree of the control valve, the amount of oil passing through the control valve, and the time it takes for the control valve to actually respond from receiving the command.

[0008] Preferably, analyzing the oil volume change of the oil reservoir in the hydraulic station based on the pre-processed operation data, and starting the cross-regional oil volume reservation scheduling based on the predicted result of the oil volume change includes the following steps: S21, extracting ambient temperature data of the oil storage tank from the pre-processed operation data, and performing thermal analysis on the ambient temperature data; S22, calculating the density and viscosity of the oil based on the thermal analysis results, and judging the fluidity of the oil during the transportation process based on the density and viscosity of the oil to judge the flowability of the oil; S23, based on the flow capacity of the oil and the oil reserve in the oil reservoir, predicting the change of the oil volume in the oil reservoir in the future time period; S24. Compare the predicted oil volume change with the critical oil volume level. If the predicted oil volume drops to the critical level, reserve oil storage tanks in other areas and perform cross-area oil volume scheduling.

[0009] Preferably, based on the flow capacity of the oil and in combination with the oil reserve in the oil reservoir, predicting the change in the amount of oil in the oil reservoir in the future time period comprises the following steps: S231, identifying and selecting the main factors affecting the change of the oil amount in the oil reservoir based on the flow capacity of the oil; S232, extracting a historical sample oil volume sequence from historical records, and determining a trend component and a periodic component of the historical sample oil volume sequence using a time series decomposition algorithm; S233, constructing and training an oil quantity prediction model based on a BP neural network, determining the number of nodes of a network input layer, a network output layer, and a network hidden layer during the training process of the oil quantity prediction model, and calculating the hidden layer output and the output layer output respectively; S234, judging whether the model error of the oil quantity prediction model is within a preset range based on the hidden layer output and the output layer output; if the model error of the oil quantity prediction model exceeds the preset range, continuously training the oil quantity prediction model; S235. The oil reserve and main factors in the oil reservoir are used as inputs of the trained oil quantity prediction model, and the trained oil quantity prediction model is used to output the prediction results of the oil quantity change in the oil reservoir in the future time period.

[0010] Preferably, the predicted oil quantity change is compared with the critical oil quantity level. If the predicted oil quantity drops to the critical level, the oil storage tanks in the remaining areas are reserved, and the cross-area oil quantity scheduling is performed, which includes the following steps: S241, comparing the oil quantity change in the oil reservoir in the future time period with the oil quantity critical level, if the oil quantity change in the oil reservoir is lower than the oil quantity critical level, executing step S242, otherwise, continuously monitoring the oil quantity change in the oil reservoir; S242, combining the deployment positions of all oil reservoirs in the hydraulic station, adopting a hierarchical method to manage the oil reservoirs in a hierarchical manner, realizing hierarchical division of the oil reservoirs, and executing reservations for the oil reservoirs at each level; S243, using a directed acyclic graph to represent the oil quantity scheduling order of the oil reservoirs at each level, wherein each node in the directed acyclic graph represents an oil reservoir, and each edge represents an oil quantity scheduling path for scheduling the oil quantity in one oil reservoir to another oil reservoir; S244, using the pruning method to optimize the oil scheduling path, eliminating redundant routes in the oil scheduling process, and at the same time selecting the optimal oil scheduling path based on the deployment positions of oil storage tanks at each level; S245. After the reservation of the oil storage tanks at each level is completed, the oil quantity scheduling is performed according to the optimal oil quantity scheduling path to adjust the oil quantity distribution among the oil storage tanks.

[0011] Preferably, in combination with the deployment positions of all oil reservoirs in the hydraulic station, a hierarchical method is adopted to manage each oil reservoir in a hierarchical manner, so as to realize the hierarchical division of each oil reservoir, and the reservation of each level of oil reservoir is performed, which includes the following steps: S2421, collecting the deployment positions of the oil reservoirs in the hydraulic system, and dividing the oil reservoirs into different levels by using a hierarchical method based on the deployment positions; S2422, calculate the dispatchable number of oil storage tanks at each level, if the dispatchable number is 1, perform the dispatch reservation operation at the preset time for the current oil storage tank, and jump to step S2423 after the dispatch reservation operation is completed; if the dispatchable number is greater than 1, jump to step S2424; S2423, determining whether all the coordinated oil storage tanks at the preset time are in an idle state, predicting the end time of the coordinated oil storage tanks in the idle state, and reserving all the coordinated oil storage tanks to start executing oil quantity scheduling at the end time; S2424. Determine the processing order according to the commonalities and priorities among the oil reservoirs at each level, and for the collaborative oil reservoir with the highest processing order, make an appointment for the priority collaborative oil reservoir according to the preset time determined in step S2422, and execute the scheduling appointment in descending order of priority.

[0012] Preferably, establishing a dynamic balance model among the oil reservoir, the hydraulic pump and the control valve, and evaluating the oil delivery state among the oil reservoir, the hydraulic pump and the control valve comprises the following steps: S31, extracting oil reservoir data, hydraulic pump data and control valve data from the operation data of the hydraulic station, and analyzing the performance parameters of the oil reservoir, hydraulic pump and control valve, the performance parameters including maximum capacity, maximum output flow, adjustment range and response time; S32, establishing a dynamic balance model, taking the oil reservoir, the hydraulic pump and the control valve as participants of the dynamic balance model respectively, and using the dynamic balance model to analyze the oil delivery state between the participants; S33. Introduce information entropy calculation into the genetic algorithm to design the fitness function, and use the fitness function to solve the dynamic equilibrium model.

[0013] Preferably, establishing a dynamic balance model, taking the oil reservoir, the hydraulic pump and the control valve as participants of the dynamic balance model respectively, and using the dynamic balance model to analyze the oil delivery state between the participants includes the following steps: S321, establishing a dynamic balance model based on the performance parameters of the oil reservoir, the hydraulic pump and the control valve, and taking the oil reservoir, the hydraulic pump and the control valve as participants of the dynamic balance model respectively; S322, forming sub-alliances between any two of the oil reservoir, hydraulic pump and control valve, and using an energy detection algorithm to perform sub-alliance sharing perception; S323. Establish a utility function for each participant. If the utility function value of the participant is greater than the utility function value of the sub-alliance to which it belongs, it indicates that the participant is inefficiently utilized under the current configuration. Then the participant is split from the alliance to which it belongs and joins another sub-alliance separately. S324. If the utility function value of any two sub-alliances after merging is greater than the sum of their independent utility function values, the two current sub-alliances are merged into a new sub-alliance; S325. After the new sub-alliance is formed, the participants in the new sub-alliance share performance parameters, and the alliance leader adjusts the performance parameters of each participant according to a predetermined decision rule, and analyzes the oil delivery status between the participants based on the adjusted performance parameters.

[0014] Preferably, the utility function is expressed as: ; In the formula, Indicates sub-alliance s The probability of missed detection; Indicates sub-alliance s The penalty function of v represents the utility function value; Indicates sub-alliance s An increasing function of the detection probability in ; m Indicates the impact on the participants’ decisions; d Indicates the distance between participants; f Represents participant attributes.

[0015] According to another aspect of the present invention, a hydraulic station remote flow control system based on the Internet of Things is also provided, and the hydraulic station remote flow control system based on the Internet of Things includes a data acquisition module, an oil quantity prediction module, a dynamic balance analysis, a fault monitoring module and a flow control module; The data acquisition module is connected with the oil quantity prediction module, the dynamic balance analysis module, the fault monitoring module and the flow control module in sequence; The data acquisition module is used to collect the operation data of the hydraulic station in real time using a preset sensor group, and transmit the operation data to the Internet of Things platform for preprocessing; The oil quantity prediction module is used to analyze the oil quantity changes in the oil reservoir in the hydraulic station based on the pre-processed operation data, and to start cross-regional oil quantity reservation scheduling based on the prediction results of the oil quantity changes; Dynamic balance analysis module, used to establish a dynamic balance model between the oil reservoir, hydraulic pump and control valve, and evaluate the oil delivery status between the oil reservoir, hydraulic pump and control valve; A fault monitoring module is used to transport the oil in the oil reservoir according to the oil transport state, and to identify the oil transport fault by using the fault monitoring model during the oil transport process; The flow control module is used to adjust the oil delivery status between the oil reservoir, the hydraulic pump and the control valve according to the identified oil delivery fault, so as to realize remote control of the oil amount.

[0016] The beneficial effects of the present invention are: 1. The present invention collects operating data in real time so as to quickly and accurately obtain the operating status of the hydraulic station, provide real-time data support for subsequent decision-making, and analyze the oil volume changes in the oil reservoir based on the operating data to effectively predict future oil demand and achieve optimal oil volume allocation. At the same time, starting cross-regional oil volume reservation scheduling can achieve cross-regional optimization of resources, ensure that the hydraulic station can operate efficiently and stably, and reduce downtime caused by insufficient oil. By establishing a dynamic balance model between the oil reservoir, hydraulic pump and control valve, the oil volume delivery status can be more accurately evaluated, providing a scientific basis for the adjustment strategy. The fault monitoring model is used to identify oil volume delivery faults during the oil volume delivery process, and problems can be discovered and handled in a timely manner, thereby achieving remote control of the oil flow rate and improving the flexibility of operation.

[0017] 2. The present invention can more accurately understand the impact of temperature changes on oil properties by performing thermal analysis on ambient temperature data, provide a scientific basis for oil management, use thermal analysis to help predict the behavior of oil under different environmental conditions, guide the effective use of oil, and avoid poor performance due to temperature changes. At the same time, based on the calculation of oil density and viscosity, the flow capacity of oil can be accurately judged to help design more effective transportation strategies, reduce energy consumption, and improve transportation efficiency. By predicting the changes in the amount of oil in the oil reservoir in future time periods, resource allocation and scheduling plans can be made in advance to avoid problems of resource shortages or surpluses.

[0018] 3. By analyzing the performance parameters of the oil reservoir, hydraulic pump and control valve, the present invention can better understand the operating limits and optimization potential of each device, thereby optimizing their performance and improving the overall efficiency of the system. At the same time, the oil reservoir, hydraulic pump and control valve are regarded as participants in the dynamic balance model, which can effectively analyze and coordinate the oil delivery status between them, ensure the coordinated operation of the system, avoid excessive or insufficient oil, and help to reasonably allocate resources among the participants through the dynamic balance model, ensure the efficient use of oil resources, and reduce energy consumption and operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. 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 paying creative work.

[0020] Figure 1 is a flow chart of a hydraulic station remote flow control method based on the Internet of Things according to an embodiment of the present invention; Figure 2It is a principle block diagram of a hydraulic station remote flow control system based on the Internet of Things according to an embodiment of the present invention.

[0021] In the figure: 1. Data acquisition module; 2. Oil quantity prediction module; 3. Dynamic balance analysis module; 4. Fault monitoring module; 5. Flow control module. DETAILED DESCRIPTION

[0022] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0023] According to an embodiment of the present invention, a method and system for remote flow control of a hydraulic station based on the Internet of Things are provided.

[0024] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the hydraulic station remote flow control method based on the Internet of Things according to an embodiment of the present invention, the hydraulic station remote flow control method based on the Internet of Things includes the following steps: S1. Use the preset sensor group to collect the operating data of the hydraulic station in real time, and transmit the operating data to the Internet of Things platform for preprocessing.

[0025] It should be noted that using a preset sensor group to collect the operating data of the hydraulic station in real time and transmitting the operating data to the Internet of Things platform for preprocessing includes the following steps: Select appropriate sensors according to monitoring requirements, and deploy sensors reasonably according to the layout and structure of the hydraulic station; collect real-time operating data of the hydraulic station through sensors, convert the real-time operating data collected by the sensors into digital signals, and ensure the accuracy and completeness of the real-time operating data; transmit the collected real-time operating data to the Internet of Things platform through various communication protocols and technologies, such as Wi-Fi, Ethernet, Bluetooth, LoRaWAN, etc.; The Internet of Things platform receives the data transmitted from the hydraulic station and pre-processes the received data, including data cleaning, denoising, correction and other steps to ensure the quality and reliability of the data; store the pre-processed data in the database for subsequent data analysis and application; establish a real-time monitoring system on the Internet of Things platform to monitor the operating status and parameter changes of the hydraulic station.

[0026] Among them, the operation data of the hydraulic station includes oil reservoir data, hydraulic pump data and control valve data.

[0027] The oil reservoir data includes the storage capacity of the oil reservoir, the oil reserve in the oil reservoir and the ambient temperature data of the oil reservoir.

[0028] The hydraulic pump data includes the amount of oil output per unit time of the hydraulic pump, the output pressure of the hydraulic pump, and the start and stop status of the hydraulic pump.

[0029] The control valve data includes the opening degree of the control valve, the amount of oil passing through the control valve, and the time it takes for the control valve to actually respond from receiving the command.

[0030] S2. Analyze the oil volume change in the oil reservoir in the hydraulic station based on the pre-processed operation data, and start cross-regional oil volume reservation scheduling based on the predicted results of the oil volume change.

[0031] Among them, analyzing the oil volume change of the oil reservoir in the hydraulic station based on the pre-processed operation data, and starting the cross-regional oil volume reservation scheduling based on the predicted result of the oil volume change includes the following steps: S21. Extracting ambient temperature data of the oil reservoir from the preprocessed operating data, and performing thermal analysis on the ambient temperature data.

[0032] It should be noted that extracting the ambient temperature data of the oil storage tank from the pre-processed operating data and performing thermal analysis on the ambient temperature data includes the following steps: According to the characteristics of ambient temperature data and analysis requirements, thermal analysis methods are used to calculate and analyze ambient temperature data accordingly. The thermal analysis methods mainly include: Temperature trend analysis: Analyze the changing trend of ambient temperature over time and detect whether there are periodic or trend changes.

[0033] Temperature distribution analysis: Conduct statistical analysis on ambient temperature data to understand the temperature distribution and its changing patterns.

[0034] Correlation analysis: Analyze the correlation between ambient temperature and other parameters, and explore the degree of association and influencing factors between them.

[0035] Interpret the thermal analysis results, analyze the characteristics and changing patterns of ambient temperature data, and make corresponding suggestions or decisions based on the analysis results, such as adjusting equipment operating parameters, optimizing equipment layout or maintenance strategies, etc., to improve the efficiency and stability of the system.

[0036] S22. Calculate the density and viscosity of the oil based on the thermal analysis results, and determine the fluidity of the oil during the transportation process based on the density and viscosity of the oil to determine the flowability of the oil.

[0037] It should be noted that calculating the oil density and oil viscosity based on the thermal analysis results, and judging the fluidity of the oil during the transportation process based on the oil density and oil viscosity, so as to judge the flowability of the oil, includes the following steps: According to the temperature data in the thermal analysis results, the density of the oil is calculated using the density calculation formula. The density of the oil is usually related to the temperature, so the effect of temperature on the density needs to be considered.

[0038] The density calculation formula varies depending on the type of oil used. The applicable density calculation formula can be obtained through empirical formulas or by referring to relevant materials. The calculation result of oil density is expressed in unit mass (such as kilograms / cubic meter).

[0039] According to the temperature data in the thermal analysis results, the viscosity of the oil is calculated using the viscosity calculation formula. The viscosity of the oil usually changes with the change of temperature, so the effect of temperature on viscosity needs to be considered.

[0040] The viscosity calculation formula varies depending on the type of oil used. The applicable viscosity calculation formula can be obtained through empirical formulas or by referring to relevant materials. The calculation result of oil viscosity is expressed in unit dynamic viscosity (such as Pascal seconds).

[0041] The density and viscosity of oil are used to determine its fluidity and flowability during the transportation process. For a fluid, its flowability is directly related to its viscosity. The higher the viscosity, the worse the flowability and the more difficult it is for the fluid to flow. The density of the oil will also affect its fluidity. A higher density may lead to greater inertia and fluid resistance, thereby reducing the fluidity of the oil, which in turn will affect the change in the amount of oil in the oil reservoir in the subsequent content.

[0042] S23. Based on the flow capacity of the oil and the oil reserve in the oil reservoir, predict the change of the oil amount in the oil reservoir in the future time period.

[0043] The process of predicting the change of the amount of oil in the oil reservoir in the future time period based on the flow capacity of the oil and the amount of oil in the oil reservoir includes the following steps: S231, identifying and selecting the main factors affecting the change of the oil amount in the oil reservoir based on the flow capacity of the oil; S232. Extracting a historical sample oil volume sequence from historical records, and using a time series decomposition algorithm to determine a trend component and a periodic component of the historical sample oil volume sequence.

[0044] It should be noted that extracting the historical sample oil volume sequence from the historical records and using the time series decomposition algorithm to determine the trend component and periodic component of the historical sample oil volume sequence includes the following steps: A sample sequence of oil volume data is obtained from historical records. The sample sequence of oil volume data is time series data indexed by timestamps, including changes in oil volume over time.

[0045] It should be noted that historical records refer to all data records about oil volume monitored over a period of time in the past. These records may include real-time readings of oil volume, timestamps, system status parameters and other information; historical sample oil volume sequences are extracted from these historical records and focus on data sequences of oil volume changes. These sequences are used to observe and analyze the changing trends and patterns of oil volume in oil reservoirs over time.

[0046] Time series decomposition is the process of decomposing time series data into three components: trend, seasonality and residual. Time series decomposition includes classical decomposition method and STL method.

[0047] The classical decomposition method decomposes the time series into long-term trend, seasonality and residual, using techniques such as moving average or exponential smoothing to estimate the trend and seasonal components, which are then subtracted from the original data to obtain the residual.

[0048] The STL method is a more flexible time series decomposition method that is better able to accommodate irregular seasonality and trends. It uses a locally weighted scatter point smoothing technique to estimate trends and seasonality and optimizes the results through an iterative process.

[0049] Trend component extraction specifically extracts trend components from the decomposed time series. Trend components represent long-term trend changes and reflect the overall trend of the time series. Periodic component extraction extracts periodic components from the decomposed time series. Periodic components reflect the repetitive patterns or periodic fluctuations of the time series within a specific period, such as weekly, monthly or annually.

[0050] Analyze the characteristics of trend and periodic components to understand the long-term trend and periodic fluctuations of oil volume changes.

[0051] S233, constructing and training an oil quantity prediction model based on a BP neural network, determining the number of nodes of the network input layer, the network output layer and the network hidden layer during the training process of the oil quantity prediction model, and calculating the hidden layer output and the output layer output respectively.

[0052] It should be noted that building and training the oil volume prediction model based on BP neural network includes the following steps: The number of input layer nodes is determined according to the number of features involved in the prediction task. For example, if the features include four factors: time, ambient temperature, pressure, and flow, the number of input layer nodes is 4.

[0053] The number of output layer nodes is determined according to the prediction target. If it is a single-value oil volume prediction, the number of output layer nodes is 1; if it is a multi-value prediction (for example, predicting the oil volume in different time periods), the number of output layer nodes may be greater than 1.

[0054] The number of hidden layer nodes is a key part in model design, affecting the model's expressiveness and learning capabilities. The number of hidden layer nodes can be determined through experimental adjustment. By trying different numbers of nodes and evaluating the performance of the model, the number of nodes that makes the model perform best on the validation set is selected.

[0055] The input of the hidden layer is mainly obtained by multiplying the connection weight between the input layer and the hidden layer by the input data, adding a bias term, and then processing it through an activation function (such as sigmoid, ReLU, etc.); the output of the hidden layer is mainly the result after processing by the activation function, which is the output of the hidden layer; the output calculation of the output layer usually does not require additional calculation. It is the output of the hidden layer, which is weighted and summed by the weight and bias term of the output layer, and then passed through the activation function of the output layer (such as linear activation function or sigmoid function); if it is a multi-value prediction, the output layer can be processed using a softmax function to obtain the probability distribution of each output value.

[0056] S234, judging whether the model error of the oil quantity prediction model is within a preset range based on the hidden layer output and the output layer output; if the model error of the oil quantity prediction model exceeds the preset range, continuously training the oil quantity prediction model; S235. The oil reserve and main factors in the oil reservoir are used as inputs of the trained oil quantity prediction model, and the trained oil quantity prediction model is used to output the prediction results of the oil quantity change in the oil reservoir in the future time period.

[0057] S24. Compare the predicted oil volume change with the oil volume critical level (referring to the preset threshold value of the oil volume in the oil reservoir). If the predicted oil volume drops to the critical level, reserve the oil reservoirs in the remaining areas and perform cross-regional oil volume scheduling.

[0058] The predicted oil volume change is compared with the critical oil volume level. If the predicted oil volume drops to the critical level, the oil storage tanks in the remaining areas are reserved, and the cross-area oil volume scheduling is performed, including the following steps: S241, comparing the oil quantity change in the oil reservoir in the future time period with the oil quantity critical level, if the oil quantity change in the oil reservoir is lower than the oil quantity critical level, executing step S242, otherwise, continuously monitoring the oil quantity change in the oil reservoir; S242. Combined with the deployment positions of all the oil reservoirs in the hydraulic station, a hierarchical method is used to manage the oil reservoirs in layers, so as to realize the hierarchical division of the oil reservoirs and execute reservations for the oil reservoirs at each layer.

[0059] It should be noted that, in combination with the deployment positions of all oil reservoirs in the hydraulic station, the hierarchical method is adopted to manage the oil reservoirs in a hierarchical manner, so as to realize the hierarchical division of the oil reservoirs, and the reservation of the oil reservoirs at each level includes the following steps: Collect the deployment locations of all oil reservoirs in the hydraulic station, including their location and quantity in the hydraulic system and their relationship with other equipment.

[0060] Determine the location level of each oil reservoir, such as ground level, underground level, etc., or divide the levels according to the structure of the hydraulic system.

[0061] The oil storage devices are divided into different levels using the stratification method. The stratification method is based on factors such as the importance, frequency of use, and functional characteristics of the oil storage devices in order to achieve effective management and control. Different stratification standards are used according to needs, such as stratification by function (such as oil storage, sedimentation, filtration, etc.), stratification by frequency of use (such as common, standby, emergency), etc.

[0062] According to the results of the stratification method, a management mechanism for oil storage tanks at each level is established, including determining the management responsible person, management process and management standards at each level.

[0063] Determine the use rights and operating procedures of oil storage tanks at each level, and implement reservation management for oil storage tanks at each level. Reservations can include pre-arrangement and scheduling of the use time, quantity, purpose, etc. of oil storage tanks to ensure the rational use of resources and the balance of supply and demand.

[0064] Among them, combined with the deployment positions of all oil reservoirs in the hydraulic station, a hierarchical method is used to manage each oil reservoir in a hierarchical manner, so as to realize the hierarchical division of each oil reservoir, and execute the reservation of each level of oil reservoir, including the following steps: S2421, collecting the deployment positions of the oil reservoirs in the hydraulic system, and dividing the oil reservoirs into different levels by using a hierarchical method based on the deployment positions; S2422, calculate the dispatchable number of oil storage tanks at each level, if the dispatchable number is 1, perform the dispatch reservation operation at the preset time for the current oil storage tank, and jump to step S2423 after the dispatch reservation operation is completed; if the dispatchable number is greater than 1, jump to step S2424; S2423, determining whether all the coordinated oil storage tanks at the preset time are in an idle state, predicting the end time of the coordinated oil storage tanks in the idle state, and reserving all the coordinated oil storage tanks to start executing oil quantity scheduling at the end time; S2424. Determine the processing order according to the commonalities and priorities among the oil reservoirs at each level, and for the collaborative oil reservoir with the highest processing order, make an appointment for the priority collaborative oil reservoir according to the preset time determined in step S2422, and execute the scheduling appointment in descending order of priority.

[0065] It should be noted that the processing order is determined according to the commonality and priority between the oil storage tanks at each level, and for the coordinated oil storage tank with the highest processing order, the priority coordinated oil storage tank is scheduled at the preset time determined in step S2422, and the scheduling reservation is executed in descending order according to the priority order, including the following steps: Analyze the commonalities and priorities among oil reservoirs at each level, for example, determine the basis for the processing order based on their functions, frequency of use, importance and other factors; commonalities include the level, type, capacity and other characteristics of the oil reservoir, while priorities are determined based on operational requirements, system safety, urgency and other factors.

[0066] The processing order between oil reservoirs at each level is determined based on commonality and priority. The processing order includes processing oil reservoirs with the same commonality first, or determining the processing order based on priority.

[0067] According to the preset time determined in step S2422, the scheduled operation time of the priority coordinated oil storage tank is determined. These times are determined based on factors such as system operation status and demand planning, and are predetermined before the oil scheduling task is executed.

[0068] At the preset time, the reservation operation is performed on the collaborative oil tank with the highest processing order, and the scheduling reservation is executed in descending order of priority. This means that the reservation operation of the oil tank with the highest priority is executed first, and then the reservation operations of other oil tanks are executed in order of gradually decreasing priority until all reservation operations are completed.

[0069] S243. Use a directed acyclic graph to represent the oil quantity scheduling order of oil reservoirs at each level, wherein each node in the directed acyclic graph represents an oil reservoir, and each edge represents an oil quantity scheduling path for scheduling the oil in one oil reservoir to another oil reservoir.

[0070] It should be noted that using a directed acyclic graph to represent the oil quantity scheduling order of each level of oil storage tanks is an effective way, which specifically includes: Each oil reservoir is regarded as a node in the graph. According to the previous hierarchical management results, each node corresponds to an oil reservoir and is arranged in the order of hierarchical division.

[0071] According to the order of oil scheduling, the scheduling order relationship between each oil reservoir is determined, and the corresponding nodes are connected with directed edges; the direction of the edge represents the flow direction of the oil, that is, from the oil supply node to the oil receiving node.

[0072] Ensure that the constructed graph is acyclic, that is, there is no path starting from a node through several edges and finally returning to the node. This is achieved by avoiding the formation of loops in the process of constructing the graph.

[0073] Adjacency matrices or adjacency lists are used to represent directed acyclic graphs. Adjacency matrices are suitable for dense graphs, while adjacency lists are suitable for sparse graphs. The rows and columns in the adjacency matrix represent the nodes in the graph, and the matrix elements represent the existence or non-existence of edges. The adjacency list stores the adjacent node information of each node in the form of a linked list or array.

[0074] The oil volume scheduling order of each oil tank is determined by topological sorting of the graph. Topological sorting ensures that the direction of all edges in the graph is from front to back, that is, it ensures that the flow direction of the oil volume meets the scheduling order requirements.

[0075] The node sequence obtained by topological sorting is used as the order of oil scheduling. In the actual oil scheduling process, the oil supply and receiving operations are performed in sequence according to this order.

[0076] S244. The pruning method is used to optimize the oil scheduling path, eliminate redundant routes in the oil scheduling process, and at the same time, the optimal oil scheduling path is selected based on the deployment positions of oil storage tanks at each level.

[0077] It should be noted that the pruning method is used to optimize the oil scheduling path, eliminate redundant routes in the oil scheduling process, and screen out the optimal oil scheduling path based on the deployment locations of oil storage tanks at each level, including the following steps: Use pruning to optimize the directed acyclic graph and eliminate redundant scheduling paths. The pruning strategies include: Remove invalid paths: Based on actual needs and constraints, remove paths that cannot meet the needs, such as paths with insufficient capacity or too long distance.

[0078] Merge similar paths: Merge paths with similar start and end points into one path, reducing the number of branches in the graph.

[0079] Eliminate loop paths: Eliminate paths that may lead to loops to ensure that the scheduling process does not fall into an infinite loop.

[0080] Combined with the deployment location information of oil storage tanks at each level, oil storage tanks that are close to the deployment location and have sufficient oil are selected as the priority choice for the scheduling path, thereby reducing the energy consumption and time cost in the oil scheduling process.

[0081] According to the optimized scheduling diagram and combined with the deployment location information, the optimal oil scheduling path is screened out. The optimal path may be the path that meets the scheduling requirements and can complete the scheduling in the shortest time.

[0082] The selected optimal path is evaluated, and various factors such as path length, oil supply and demand balance, energy consumption, etc. are considered to further optimize the path selection.

[0083] S245. After the reservation of the oil storage tanks at each level is completed, the oil quantity scheduling is performed according to the optimal oil quantity scheduling path to adjust the oil quantity distribution among the oil storage tanks.

[0084] S3. Establish a dynamic balance model among the oil reservoir, hydraulic pump and control valve to evaluate the oil delivery status among the oil reservoir, hydraulic pump and control valve.

[0085] Among them, establishing a dynamic balance model between the oil reservoir, the hydraulic pump and the control valve, and evaluating the oil delivery state between the oil reservoir, the hydraulic pump and the control valve include the following steps: S31, extracting oil reservoir data, hydraulic pump data and control valve data from the operation data of the hydraulic station, and analyzing the performance parameters of the oil reservoir, hydraulic pump and control valve, the performance parameters including maximum capacity, maximum output flow, adjustment range and response time; S32. Establish a dynamic balance model, take the oil reservoir, hydraulic pump and control valve as participants of the dynamic balance model respectively, and use the dynamic balance model to analyze the oil delivery status between the participants.

[0086] Among them, establishing a dynamic balance model, taking the oil reservoir, hydraulic pump and control valve as participants of the dynamic balance model respectively, and using the dynamic balance model to analyze the oil delivery state between the participants includes the following steps: S321. A dynamic balance model is established based on the performance parameters of the oil reservoir, the hydraulic pump and the control valve, and the oil reservoir, the hydraulic pump and the control valve are respectively used as participants of the dynamic balance model.

[0087] It should be noted that the dynamic balance model is a dynamic balance model based on the game theory model. Since multiple sub-alliances can be formed between the oil reservoir, hydraulic pump and control valve, the system optimization and performance improvement can be achieved through cooperation and shared perception between sub-alliances. At the same time, the energy detection algorithm can be used for shared perception of sub-alliances.

[0088] The oil reservoir, hydraulic pump and control valve are combined in pairs to form multiple sub-alliances. Each sub-alliance consists of two components, such as the oil reservoir-hydraulic pump sub-alliance, the oil reservoir-control valve sub-alliance, the hydraulic pump-control valve sub-alliance, etc.

[0089] In each sub-alliance, energy detection algorithms are used for shared perception. The energy detection algorithm is based on sensor data from components such as oil reservoirs, hydraulic pumps, and control valves, and obtains information about the system status by detecting energy changes and trends. Components in a sub-alliance can share each other's perception data, for example, a hydraulic pump can sense changes in the oil level of an oil reservoir, and a control valve can sense changes in the pressure of a hydraulic pump, thereby increasing the system's common perception and understanding of each component.

[0090] In the sub-alliance, components achieve shared perception through information exchange and collaboration. For example, the hydraulic pump can send a request to the oil reservoir to obtain oil level information, and the control valve can send a request to the hydraulic pump to obtain pressure information; the components in the sub-alliance can jointly analyze the perception data, perform state estimation and prediction, and jointly make decisions and adjust strategies to achieve system optimization and performance improvement.

[0091] Combined with the shared perception and collaboration of the sub-alliance, the performance of the hydraulic system can be improved by optimizing strategies and adjusting parameters. For example, the supply speed of the hydraulic pump can be adjusted according to the oil level change of the oil reservoir, and the opening of the control valve can be adjusted according to the pressure change of the hydraulic pump.

[0092] Through cooperation and shared perception among sub-alliances, system-level optimization and performance improvement can be achieved, improving the efficiency, stability and reliability of the hydraulic system.

[0093] S322, forming sub-alliances between any two of the oil reservoir, hydraulic pump and control valve, and using an energy detection algorithm to perform sub-alliance sharing perception; S323. Establish a utility function for each participant. If the utility function value of the participant is greater than the utility function value of the sub-alliance to which it belongs, it indicates that the participant is being used inefficiently under the current configuration. In this case, the participant is split from the alliance to which it belongs and joins another sub-alliance separately.

[0094] Among them, the expression of the utility function is: ; In the formula, Indicates sub-alliance s The probability of missed detection; Indicates sub-alliance s The penalty function of v represents the utility function value; Indicates sub-alliance s An increasing function of the detection probability in ; m Indicates the impact on the participants’ decisions; d Indicates the distance between participants; f Represents participant attributes.

[0095] It should be noted that in the game theory model, concepts such as effect function, utility function, probability of missed detection, penalty function, detection probability increasing function, decision-making influence of participants, distance between participants and participant attributes are involved. They are usually used to study how multiple participants (individuals or organizations) interact strategically based on their respective goals in a specific environment.

[0096] The missed detection probability usually refers to the probability that a system or model fails to detect a specific event (such as fraud, intrusion, etc.). In this invention, it refers to the probability that the sub-alliance fails to successfully identify the target event when performing its tasks (such as monitoring or detecting specific behaviors).

[0097] In game theory, penalty functions are used to express the costs or losses incurred by participants for not following the rules or failing to achieve the expected goals. For a sub-alliance, this function describes the penalties or costs faced when the sub-alliance fails to achieve its monitoring or enforcement goals, such as financial losses or reputation damage due to missed inspections.

[0098] The increasing function of the detection probability in the sub-alliance s is a function that represents the increase in the probability of successfully detecting the target event after the sub-alliance s takes a certain measure or strategy. This increasing function is usually related to resource investment, technology improvement or strategy adjustment, and is used to evaluate how these changes improve the efficiency or effectiveness of detection.

[0099] Impact on the decision-making of participants: This refers to how the strategy choice of the sub-alliance affects the decision-making of its members or other participants. In a multi-party interactive game, the strategy change of one participant often affects the optimal strategy choice of other participants, thereby affecting the equilibrium state of the entire game.

[0100] Participant attributes refer to various characteristics of participants, such as strategy selection, resource ownership, risk preference, ability level, etc.

[0101] S324. If the utility function value of any two sub-alliances after merging is greater than the sum of their independent utility function values, the two current sub-alliances are merged into a new sub-alliance; S325. After the new sub-alliance is formed, the participants in the new sub-alliance share performance parameters, and the alliance leader adjusts the performance parameters of each participant according to a predetermined decision rule, and analyzes the oil delivery status between the participants based on the adjusted performance parameters.

[0102] S33. Introduce information entropy calculation into the genetic algorithm to design the fitness function, and use the fitness function to solve the dynamic equilibrium model.

[0103] It should be noted that the introduction of information entropy calculation to design a fitness function in a genetic algorithm and the use of the fitness function to solve a dynamic equilibrium model include the following steps: Taking information entropy as part of the fitness function, a comprehensive fitness function is designed to evaluate the pros and cons of each participant.

[0104] The fitness function comprehensively considers information entropy, system performance indicators (such as energy consumption, response time, etc.), and other constraints (such as system stability, resource utilization, etc.).

[0105] The designed fitness function is used as the evaluation criterion of the genetic algorithm, and the genetic algorithm is used to search for the optimal solution. The genetic algorithm generates new system configurations (individuals) through continuous iterative evolution, evaluates its performance based on the fitness function, and selects individuals with higher fitness for reproduction and evolution, thereby gradually optimizing the system configuration.

[0106] During the iterative process of the genetic algorithm, the system configuration is continuously updated, so that the information entropy of the system gradually decreases and the system performance is gradually optimized. When a certain number of iterations is reached or the stopping condition is met, the optimal system configuration obtained is the solution of the dynamic equilibrium model, which can enable the hydraulic system to achieve optimal performance and stability under the current working conditions.

[0107] The optimal system configuration obtained by the genetic algorithm is analyzed to evaluate its practicality and feasibility. According to actual needs and system characteristics, the optimal system configuration is adjusted and optimized to meet more precise performance requirements or cope with specific changes in operating conditions.

[0108] S4. The oil in the oil reservoir is transported according to the oil transport status, and the oil transport fault is identified by using the fault monitoring model during the oil transport process.

[0109] It should be noted that the oil in the oil reservoir is transported according to the oil transport state, and the oil transport fault is identified by using the fault monitoring model during the oil transport process, including the following steps: According to the monitoring results of the oil delivery status, corresponding oil delivery operations are performed, including controlling the hydraulic pump and the control valve, and adjusting the flow direction and speed of the oil to achieve oil delivery between oil reservoirs.

[0110] Establish a fault monitoring model to identify possible faults and abnormal conditions that may occur during traffic delivery, and perform fault diagnosis and prediction based on monitoring data and historical fault cases based on machine learning algorithms or rule-based methods.

[0111] The fault monitoring model should include status monitoring and anomaly detection of each component in the hydraulic system, as well as analysis and identification of possible fault types and causes.

[0112] When the fault monitoring model detects an oil delivery fault, it will promptly perform fault diagnosis and processing, including suspending delivery operations, adjusting system parameters, replacing faulty components, and other measures to restore the normal operation of the system.

[0113] S5. Adjust the oil delivery status between the oil reservoir, the hydraulic pump and the control valve according to the identified oil delivery fault to achieve remote control of the oil amount.

[0114] It should be noted that adjusting the oil delivery state between the oil reservoir, the hydraulic pump and the control valve according to the identified oil delivery fault to achieve remote control of the oil volume includes the following steps: It is necessary to identify and analyze possible causes of oil delivery failure, including but not limited to sudden changes in oil volume, abnormal pressure, increased temperature and other signals.

[0115] Once the cause of the oil delivery failure is determined, the oil delivery status between the oil reservoir, hydraulic pump and control valve is adjusted according to the identified problem, which includes adjusting the operating parameters of the hydraulic pump (such as flow and pressure), replacing or repairing the damaged control valve, or adjusting the oil level in the oil reservoir to ensure smooth oil flow and system balance.

[0116] After the adjustment is implemented, the system performance needs to be re-evaluated to ensure that the measures taken have effectively solved the oil delivery failure and have not introduced new problems. In addition, simulation and prediction tools in existing technologies can be used to further optimize system performance and prevent future problems.

[0117] like Figure 2 As shown, according to another embodiment of the present invention, a hydraulic station remote flow control system based on the Internet of Things is also provided, and the hydraulic station remote flow control system based on the Internet of Things includes a data acquisition module 1, an oil quantity prediction module 2, a dynamic balance analysis module 3, a fault monitoring module 4 and a flow control module 5; The data acquisition module 1 is connected with the oil quantity prediction module 2, the dynamic balance analysis module 3, the fault monitoring module 4 and the flow control module 5 in sequence; The data acquisition module 1 is used to collect the operation data of the hydraulic station in real time using a preset sensor group, and transmit the operation data to the Internet of Things platform for preprocessing; The oil quantity prediction module 2 is used to analyze the oil quantity change of the oil reservoir in the hydraulic station based on the pre-processed operation data, and to start the cross-regional oil quantity reservation scheduling based on the prediction result of the oil quantity change; Dynamic balance analysis module 3, used to establish a dynamic balance model between the oil reservoir, the hydraulic pump and the control valve, and evaluate the oil delivery status between the oil reservoir, the hydraulic pump and the control valve; A fault monitoring module 4 is used to transport the oil in the oil reservoir according to the oil transport state, and to identify the oil transport fault by using the fault monitoring model during the oil transport process; The flow control module 5 is used to adjust the oil delivery state between the oil reservoir, the hydraulic pump and the control valve according to the identified oil delivery fault, so as to realize remote control of the oil amount.

[0118] In summary, with the help of the above-mentioned technical scheme of the present invention, the present invention can quickly and accurately obtain the operating status of the hydraulic station by collecting operating data in real time, providing real-time data support for subsequent decision-making, and analyzing the oil volume changes in the oil reservoir based on the operating data can effectively predict future oil demand and achieve optimal oil volume configuration. At the same time, starting cross-regional oil volume reservation scheduling can achieve cross-regional optimization of resources, ensure that the hydraulic station can operate efficiently and stably, and reduce downtime caused by insufficient oil. By establishing a dynamic balance model between the oil reservoir, hydraulic pump and control valve, the oil volume delivery status can be more accurately evaluated to provide a scientific basis for the adjustment strategy. The fault monitoring model is used to identify oil volume delivery faults during the oil volume delivery process, and problems can be discovered and handled in time, thereby realizing remote control of the oil flow rate and improving the flexibility of operation. The present invention can more accurately understand the impact of temperature changes on oil properties by performing thermal analysis on ambient temperature data, providing a scientific basis for oil management, and using thermal The analysis helps predict the behavior of oil under different environmental conditions, guides the effective use of oil, and avoids poor performance due to temperature changes. At the same time, based on the calculation of oil density and viscosity, the flow capacity of oil can be accurately judged, helping to design more effective delivery strategies, reduce energy consumption, and improve delivery efficiency. By predicting the changes in the amount of oil in the oil reservoir in future time periods, resource allocation and scheduling plans can be made in advance to avoid resource shortages or surpluses. The present invention can better understand the operating limits and optimization potential of each device by analyzing the performance parameters of the oil reservoir, hydraulic pump and control valve, thereby optimizing their performance and improving the overall efficiency of the system. At the same time, the oil reservoir, hydraulic pump and control valve are regarded as participants in the dynamic balance model, which can effectively analyze and coordinate the oil delivery status between them, ensure the coordinated operation of the system, avoid excessive or insufficient oil, and help to reasonably allocate resources among the participants through the dynamic balance model to ensure that oil resources are efficiently utilized while reducing energy consumption and operating costs.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A remote flow control method for a hydraulic station based on the Internet of Things, characterized in that: The remote flow control method of the hydraulic station based on the Internet of Things includes the following steps: S1. Use the preset sensor group to collect the operating data of the hydraulic station in real time, and transmit the operating data to the Internet of Things platform for preprocessing; S2. Analyze the oil volume change of the oil reservoir in the hydraulic station based on the pre-processed operation data, and start cross-regional oil volume reservation scheduling based on the predicted results of the oil volume change; S3, establish a dynamic balance model between the oil reservoir, the hydraulic pump and the control valve, and evaluate the oil delivery status between the oil reservoir, the hydraulic pump and the control valve; S4, delivering the oil in the oil reservoir according to the oil delivery state, and identifying the oil delivery fault by using the fault monitoring model during the oil delivery process; S5. Adjust the oil delivery status between the oil reservoir, the hydraulic pump and the control valve according to the identified oil delivery fault to achieve remote control of the oil amount.

2. According to the method of claim 1, the remote flow control method of a hydraulic station based on the Internet of Things is characterized in that: The operation data of the hydraulic station includes oil reservoir data, hydraulic pump data and control valve data; The oil reservoir data includes the storage capacity of the oil reservoir, the oil reserve in the oil reservoir and the ambient temperature data of the oil reservoir; The hydraulic pump data includes the output oil volume per unit time of the hydraulic pump, the output pressure of the hydraulic pump and the start / stop status of the hydraulic pump; The control valve data includes the opening degree of the control valve, the amount of oil passing through the control valve, and the actual response time of the control valve from receiving the command.

3. The method for remote flow control of a hydraulic station based on the Internet of Things according to claim 2 is characterized in that: The method of analyzing the oil volume change of the oil reservoir in the hydraulic station based on the pre-processed operation data and starting the cross-regional oil volume reservation scheduling based on the predicted result of the oil volume change includes the following steps: S21, extracting ambient temperature data of the oil storage tank from the preprocessed operation data, and performing thermal analysis on the ambient temperature data; S22, calculating the density and viscosity of the oil based on the thermal analysis results, and judging the fluidity of the oil during the transportation process based on the density and viscosity of the oil to judge the flowability of the oil; S23, based on the flow capacity of the oil and the oil reserve in the oil reservoir, predicting the change of the oil volume in the oil reservoir in the future time period; S24. Compare the predicted oil volume change with the critical oil volume level. If the predicted oil volume drops to the critical level, reserve oil storage tanks in other areas and perform cross-area oil volume scheduling.

4. The method for remote flow control of a hydraulic station based on the Internet of Things according to claim 3 is characterized in that: The method of predicting the change of the amount of oil in the oil reservoir in the future time period based on the flow capacity of the oil and the amount of oil in the oil reservoir comprises the following steps: S231, identifying and selecting the main factors affecting the change of the oil amount in the oil reservoir based on the flow capacity of the oil; S232, extracting a historical sample oil volume sequence from historical records, and determining a trend component and a periodic component of the historical sample oil volume sequence using a time series decomposition algorithm; S233, constructing and training an oil quantity prediction model based on a BP neural network, determining the number of nodes of a network input layer, a network output layer, and a network hidden layer during the training process of the oil quantity prediction model, and calculating the hidden layer output and the output layer output respectively; S234, judging whether the model error of the oil quantity prediction model is within a preset range based on the hidden layer output and the output layer output; if the model error of the oil quantity prediction model exceeds the preset range, continuously training the oil quantity prediction model; S235. The oil reserve and main factors in the oil reservoir are used as inputs of the trained oil quantity prediction model, and the trained oil quantity prediction model is used to output the prediction results of the oil quantity change in the oil reservoir in the future time period.

5. The method for remote flow control of a hydraulic station based on the Internet of Things according to claim 4 is characterized in that: The predicted oil volume change is compared with the oil volume critical level. If the predicted oil volume drops to the critical level, the oil storage tanks in other areas are reserved, and cross-area oil volume scheduling is performed, which includes the following steps: S241, comparing the oil quantity change in the oil reservoir in the future time period with the oil quantity critical level, if the oil quantity change in the oil reservoir is lower than the oil quantity critical level, executing step S242, otherwise, continuously monitoring the oil quantity change in the oil reservoir; S242, combining the deployment positions of all oil reservoirs in the hydraulic station, adopting a hierarchical method to manage the oil reservoirs in a hierarchical manner, realizing hierarchical division of the oil reservoirs, and executing reservations for the oil reservoirs at each level; S243, using a directed acyclic graph to represent the oil quantity scheduling order of the oil reservoirs at each level, wherein each node in the directed acyclic graph represents an oil reservoir, and each edge represents an oil quantity scheduling path for scheduling the oil quantity in one oil reservoir to another oil reservoir; S244, using the pruning method to optimize the oil scheduling path, eliminating redundant routes in the oil scheduling process, and at the same time selecting the optimal oil scheduling path based on the deployment positions of oil storage tanks at each level; S245. After the reservation of the oil storage tanks at each level is completed, the oil quantity scheduling is performed according to the optimal oil quantity scheduling path to adjust the oil quantity distribution among the oil storage tanks.

6. The method for remote flow control of a hydraulic station based on the Internet of Things according to claim 5 is characterized in that: The method of combining the deployment positions of all the oil reservoirs in the hydraulic station and adopting the hierarchical method to manage the oil reservoirs in a hierarchical manner, realizing the hierarchical division of the oil reservoirs, and executing the reservation of the oil reservoirs at each level includes the following steps: S2421, collecting the deployment positions of the oil reservoirs in the hydraulic system, and dividing the oil reservoirs into different levels by using a hierarchical method based on the deployment positions; S2422, calculate the dispatchable number of oil storage tanks at each level, if the dispatchable number is 1, perform the dispatch reservation operation at the preset time for the current oil storage tank, and jump to step S2423 after the dispatch reservation operation is completed; if the dispatchable number is greater than 1, jump to step S2424; S2423, determining whether all the coordinated oil storage tanks at the preset time are in an idle state, predicting the end time of the coordinated oil storage tanks in the idle state, and reserving all the coordinated oil storage tanks to start executing oil quantity scheduling at the end time; S2424. Determine the processing order according to the commonalities and priorities among the oil reservoirs at each level, and for the collaborative oil reservoir with the highest processing order, make an appointment for the priority collaborative oil reservoir according to the preset time determined in step S2422, and execute the scheduling appointment in descending order of priority.

7. The method for remote flow control of a hydraulic station based on the Internet of Things according to claim 6 is characterized in that: The establishment of a dynamic balance model between the oil reservoir, the hydraulic pump and the control valve and the evaluation of the oil delivery state between the oil reservoir, the hydraulic pump and the control valve comprises the following steps: S31, extracting oil reservoir data, hydraulic pump data and control valve data from the operation data of the hydraulic station, and analyzing performance parameters of the oil reservoir, hydraulic pump and control valve, wherein the performance parameters include maximum capacity, maximum output flow, adjustment range and response time; S32, establishing a dynamic balance model, taking the oil reservoir, the hydraulic pump and the control valve as participants of the dynamic balance model respectively, and using the dynamic balance model to analyze the oil delivery state between the participants; S33. Introduce information entropy calculation into the genetic algorithm to design the fitness function, and use the fitness function to solve the dynamic equilibrium model.

8. The method for remote flow control of a hydraulic station based on the Internet of Things according to claim 7 is characterized in that: The establishment of the dynamic balance model, taking the oil reservoir, the hydraulic pump and the control valve as participants of the dynamic balance model respectively, and using the dynamic balance model to analyze the oil delivery state between the participants includes the following steps: S321, establishing a dynamic balance model based on the performance parameters of the oil reservoir, the hydraulic pump and the control valve, and taking the oil reservoir, the hydraulic pump and the control valve as participants of the dynamic balance model respectively; S322, forming sub-alliances between any two of the oil reservoir, hydraulic pump and control valve, and using an energy detection algorithm to perform sub-alliance sharing perception; S323. Establish a utility function for each participant. If the utility function value of the participant is greater than the utility function value of the sub-alliance to which it belongs, it indicates that the participant is inefficiently utilized under the current configuration. Then the participant is split from the alliance to which it belongs and joins another sub-alliance separately. S324. If the utility function value of any two sub-alliances after merging is greater than the sum of their independent utility function values, the two current sub-alliances are merged into a new sub-alliance; S325. After the new sub-alliance is formed, the participants in the new sub-alliance share performance parameters, and the alliance leader adjusts the performance parameters of each participant according to a predetermined decision rule, and analyzes the oil delivery status between the participants based on the adjusted performance parameters.

9. The method for remote flow control of a hydraulic station based on the Internet of Things according to claim 8, characterized in that: The expression of the utility function is: ； In the formula, Indicates sub-alliance s The probability of missed detection; Indicates sub-alliance s The penalty function of v represents the utility function value; Indicates sub-alliance s An increasing function of the detection probability in ; m Indicates the impact on the participants’ decisions; d Indicates the distance between participants; f Represents participant attributes.

10. A hydraulic station remote flow control system based on the Internet of Things, used to implement the hydraulic station remote flow control method based on the Internet of Things as described in any one of claims 1 to 9, characterized in that: The hydraulic station remote flow control system based on the Internet of Things includes a data acquisition module, an oil volume prediction module, a dynamic balance analysis module, a fault monitoring module and a flow control module; The data acquisition module is connected to the oil quantity prediction module, the dynamic balance analysis module, the fault monitoring module and the flow control module in sequence; The data acquisition module is used to collect the operating data of the hydraulic station in real time using a preset sensor group, and transmit the operating data to the Internet of Things platform for preprocessing; The oil quantity prediction module is used to analyze the oil quantity change of the oil reservoir in the hydraulic station based on the pre-processed operation data, and start the cross-regional oil quantity reservation scheduling based on the prediction result of the oil quantity change; The dynamic balance analysis module is used to establish a dynamic balance model between the oil reservoir, the hydraulic pump and the control valve, and evaluate the oil delivery status between the oil reservoir, the hydraulic pump and the control valve; The fault monitoring module is used to transport the oil in the oil reservoir according to the oil transport state, and to identify the oil transport fault by using the fault monitoring model during the oil transport process; The flow control module is used to adjust the oil delivery state between the oil reservoir, the hydraulic pump and the control valve according to the identified oil delivery fault, so as to realize remote control of the oil amount.

Images