A method, device, equipment and storage medium for preventing water hammer in long pipelines

Abstract

The present invention discloses a method for preventing water hammer in long pipelines. By using a support vector machine to generate support vectors and other parameters based on historical actual data combined with the changing rules of data output by a single sensor and the correlation characteristics between data output by multiple sensors, the occurrence of water hammer can be accurately determined. It adopts a combination of theory and data drive, which reduces the demand for data, and can update support vectors and expand margins based on actual data. It can update dynamic boundaries online, accumulate data based on actual production conditions, and autonomously expand its dynamic range. The present invention also provides a device for preventing water hammer in long pipelines, a device for preventing water hammer in long pipelines, and a computer-readable storage medium, which also have the above-mentioned beneficial effects.

Description

Technical Field

[0001] The present invention relates to the technical field of pipelines, and in particular to a method for preventing water hammer in a long pipeline, a device for preventing water hammer in a long pipeline, an equipment for preventing water hammer in a long pipeline, and a computer-readable storage medium. Background Art

[0002] In long pipeline transportation systems, process switching, pump start and stop, and valve opening and closing can cause pipeline water hammer, which can cause pipeline vibration and loud noise. When water hammer occurs, the high pressure value may be many times the normal pressure, causing the pipeline material to bear great stress and may cause pipeline damage. Repeated changes in pressure can cause vibration of pipelines and equipment, resulting in equipment damage.

[0003] In the prior art, the opening and closing action of the switch valve is usually controlled, and the water hammer pressure rise value of the fluid generated is minimized or less than a predetermined value when the opening and closing action time of the switch valve is constant. However, in the prior art, it cannot dynamically adapt to the actual situation in real time. When the actual situation changes, it is difficult to update the existing technical solution in time, resulting in reduced usability and timeliness. Therefore, how to provide an automated method for preventing water hammer in long pipelines is an urgent problem to be solved by those skilled in the art. Summary of the invention

[0004] The purpose of the present invention is to provide a method for preventing water hammer in long pipelines, which can automatically and timely adjust the control scheme to actively prevent water hammer problems in long infusion pipelines; the present invention also provides a device for preventing water hammer in long pipelines, a device for preventing water hammer in long pipelines, and a computer-readable storage medium, which can automatically and timely adjust the control scheme to actively prevent water hammer problems in long infusion pipelines.

[0005] In order to solve the above technical problems, the present invention provides a method for preventing water hammer in a long pipeline, comprising:

[0006] Obtain the actual data generated in real time by sensors distributed in long infusion pipelines;

[0007] Converting the actual data into an actual vector;

[0008] When the actual vector crosses the hyperplane where the pre-trained support vector is located, the control device of the long infusion pipeline is controlled based on the pre-set expansion margin; the support vector is a support vector determined in advance by a support vector machine based on historical actual data and water hammer data; the water hammer data includes the change law of a single sensor output data and the correlation characteristics between multiple sensor output data; the hyperplane corresponds to the support vector, and the maximum value of the expansion margin corresponds to the maximum interval hyperplane corresponding to the support vector;

[0009] Detecting the actual water hammer situation corresponding to the actual vector crossing the hyperplane by using a water hammer criterion;

[0010] The support vector and / or the expansion margin are adjusted according to the actual water hammer situation.

[0011] Optionally, the adjusting the support vector and / or the expansion margin according to the actual water hammer situation includes:

[0012] When the actual water hammer situation is that no water hammer occurs and the actual vector exceeds the plane corresponding to the expansion margin, the support vector is moved forward.

[0013] Optionally, the adjusting the support vector and / or the expansion margin according to the actual water hammer situation includes:

[0014] When the actual water hammer situation is water hammer occurring, the expansion margin is adjusted.

[0015] Optionally, when the actual water hammer situation is water hammer, adjusting the expansion margin includes:

[0016] When the actual water hammer situation is water hammer, and the actual vector does not exceed the plane corresponding to the expansion margin, the expansion margin is reduced.

[0017] Optionally, also include:

[0018] Obtain historical actual data generated by sensors distributed in long infusion pipelines;

[0019] Acquire water hammer data generated by the sensor when simulating water hammer occurring in the long infusion pipeline;

[0020] Generate a feature vector according to the historical actual data and the water hammer data;

[0021] A support vector machine is called to determine the support vector, the hyperplane and the maximum margin hyperplane according to the feature vector.

[0022] Optionally, generating a feature vector according to the historical actual data and the water hammer data includes:

[0023] The dimension of the historical actual data and the water hammer data is reduced to generate the feature vector.

[0024] Optionally, before generating a feature vector according to the historical actual data and the water hammer data, the method further includes:

[0025] Noise reduction is performed on the historical actual data and the water hammer data.

[0026] The present invention also provides a device for preventing water hammer in a long pipeline, comprising:

[0027] The actual data acquisition module is used to acquire the actual data generated in real time by sensors distributed in the long infusion pipeline;

[0028] A conversion module, used for converting the actual data into an actual vector;

[0029] A control module, used for controlling the control device of the long infusion pipeline based on a preset expansion margin when the actual vector crosses the hyperplane where the pre-trained support vector is located; the support vector is a support vector pre-determined by a support vector machine according to historical actual data and water hammer data; the water hammer data includes the variation law of a single sensor output data and the correlation characteristics between multiple sensor output data; the hyperplane corresponds to the support vector, and the maximum value of the expansion margin corresponds to the maximum interval hyperplane corresponding to the support vector;

[0030] A criterion detection module, used for detecting the actual water hammer situation corresponding to the actual vector crossing the hyperplane by using the water hammer criterion;

[0031] An adjustment module is used to adjust the support vector and / or the expansion margin according to the actual water hammer situation.

[0032] The present invention also provides a device for preventing water hammer in a long pipeline, comprising:

[0033] Memory for storing computer programs;

[0034] A processor is used to implement the steps of any of the above-mentioned methods for preventing water hammer in a long pipeline when executing the computer program.

[0035] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for preventing water hammer in a long pipeline as described in any one of the above items are implemented.

[0036] A method for preventing water hammer in a long pipeline provided by the present invention comprises acquiring actual data generated in real time by sensors distributed in the long infusion pipeline; converting the actual data into actual vectors; when the actual vector crosses the hyperplane where the pre-trained support vector is located, controlling the control device of the long infusion pipeline based on the pre-set expansion margin; the support vector is a support vector determined in advance by a support vector machine based on historical actual data and water hammer data; the water hammer data includes the variation law of the output data of a single sensor and the correlation characteristics between the output data of multiple sensors; the hyperplane corresponds to the support vector, and the maximum value of the expansion margin corresponds to the maximum interval hyperplane corresponding to the support vector; the actual water hammer situation corresponding to the actual vector crossing the hyperplane is detected by a water hammer criterion; and the support vector and / or the expansion margin are adjusted according to the actual water hammer situation.

[0037] By using a support vector machine to generate support vectors and other parameters based on historical actual data combined with the changing rules of data output by a single sensor and the correlation characteristics between output data from multiple sensors, the occurrence of water hammer can be accurately determined. It adopts a combination of theory and data-driven methods to reduce the demand for data, and can update support vectors and expand margins based on actual data. It can update dynamic boundaries online, accumulate data based on actual production conditions, and autonomously expand its dynamic range.

[0038] The present invention also provides a device for preventing water hammer in a long pipeline, an apparatus for preventing water hammer in a long pipeline, and a computer-readable storage medium, which also have the above-mentioned beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings required for use in the embodiments or the description of the prior art 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.

[0040] Figure 1 A flow chart of a method for preventing water hammer in a long pipeline provided by an embodiment of the present invention;

[0041] Figure 2 A flowchart of a specific method for preventing water hammer in a long pipeline provided by an embodiment of the present invention;

[0042] Figure 3 A structural block diagram of a device for preventing water hammer in a long pipeline provided by an embodiment of the present invention;

[0043] Figure 4A structural block diagram of a device for preventing water hammer in a long pipeline provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The core of the present invention is to provide a method for preventing water hammer in long pipelines. In the prior art, the opening and closing actions of the switch valve are usually controlled so that the water hammer pressure rise value of the fluid generated is minimized or less than a predetermined value when the opening and closing action time of the switch valve is constant. However, in the prior art, it cannot dynamically adapt to the actual situation in real time. When the actual situation changes, it is difficult to update the existing technical solution in time, resulting in reduced availability and timeliness.

[0045] The method for preventing water hammer in long pipelines provided by the present invention can accurately determine the occurrence of water hammer by using a support vector machine to generate parameters such as support vectors based on historical actual data combined with the changing rules of data output by a single sensor and the correlation characteristics between output data of multiple sensors. It adopts a combination of theory and data-driven approach to reduce the demand for data, and can update support vectors and expand margins based on actual data. It can update dynamic boundaries online, accumulate data based on actual production conditions, and autonomously expand its dynamic range.

[0046] In order to enable those skilled in the art to better understand the scheme of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0047] Please refer to Figure 1 , Figure 1 The present invention provides a flow chart of a method for preventing water hammer in a long pipeline.

[0048] See also Figure 1 In an embodiment of the present invention, a method for preventing water hammer in a long pipeline includes:

[0049] S101: Acquire actual data generated in real time by sensors distributed in the long infusion pipeline.

[0050] In an embodiment of the present invention, a sensor needs to be set in the long infusion pipeline to be detected, and usually a plurality of sensors are distributed in the long infusion pipeline. The sensor usually includes a pressure sensor and a flow sensor to meet the most basic detection requirements. In an embodiment of the present invention, it is necessary to reasonably select the placement position of each sensor according to the detection accuracy index. The specific type of the sensor can be set according to the actual situation, and is not specifically limited here.

[0051] In this step, the actual data generated by the sensors distributed in the long infusion pipeline in real time will be obtained, so that the water hammer situation can be detected in real time according to the actual data in the subsequent steps. The content of the actual data also needs to be set according to the actual situation, and no specific limitation is made here.

[0052] S102: Convert the actual data into an actual vector.

[0053] In this step, the actual data will be converted into actual vectors so as to be compared with the support vectors and hyperplanes calculated by the support vector machine in the subsequent steps. Specifically, in this step, the original high-dimensional actual data is usually reduced in dimension to form an actual vector, that is, this step usually includes: reducing the dimension of the actual data to generate the actual vector. The specific dimensionality reduction method can be reduced in dimension by parameter reduction, cluster analysis, a new discriminant analysis method, etc., which is not specifically limited here, and the specific effect needs to be determined according to the actual data.

[0054] S103: When the actual vector crosses the hyperplane where the pre-trained support vector is located, the control device of the long infusion pipeline is controlled based on the pre-set expansion margin.

[0055] In an embodiment of the present invention, the support vector is a support vector determined in advance by a support vector machine based on historical actual data and water hammer data; the water hammer data includes the change law of a single sensor output data and the correlation characteristics between multiple sensor output data; the hyperplane corresponds to the support vector, and the maximum value of the expansion margin corresponds to the maximum interval hyperplane corresponding to the support vector.

[0056] In the embodiment of the present invention, it is necessary to determine the support vector in advance based on the historical actual data and the water hammer data, wherein the historical actual data is the actual data generated before the water hammer detection is performed this time, and the water hammer data specifically includes the variation law of the output data of a single sensor, and the correlation characteristics between the output data of multiple sensors. That is, in the embodiment of the present invention, it is necessary to establish a long infusion pipeline model in advance according to the actual situation of the pipeline to be tested, and then calculate through the model, when water hammer occurs, simulate the variation law of the output data of a single sensor, and when water hammer occurs, simulate the correlation characteristics between the output data of multiple sensors. Usually, the variation law of a single-point pressure sensor and the correlation characteristics of a multi-point pressure sensor are simulated. Further, the variation law of the above-mentioned sensor can also be corrected through a water hammer experiment. Since in actual situations, there are fewer cases of water hammer in the pipeline, the data generated when water hammer occurs is also less. In order to facilitate the learning of the support vector machine in the embodiment of the present invention, a theoretical model, i.e., the above-mentioned long infusion pipeline model, is specifically established in the embodiment of the present invention, and the experimental correction is conducted to establish a water hammer criterion standard, i.e., the above-mentioned water hammer data. Afterwards, the support vector machine is classified and learned based on the water hammer data and actual data to generate support vectors and related data that can be used for advance warning.

[0057] The support vector machine will output the support vector, the hyperplane confirmed by the support vector, and the maximum margin hyperplane according to the data. Then, the maximum value of the expansion margin is determined according to the maximum margin hyperplane. The position of the actual vector and the distance of each hyperplane reflect the probability of water hammer. In the subsequent steps, the expansion margin will be adjusted according to the specific situation of the actual data to reduce the probability of misclassification.

[0058] In this step, when the above-mentioned actual vector crosses the hyperplane where the pre-trained support vector is located, the control device of the long infusion pipeline is controlled based on the pre-set expansion margin. The above-mentioned control device is usually a valve and a pump set in the long infusion pipeline. Since the occurrence of water hammer is closely related to the equipment status, the switch size, switch speed and other parameters of the valve and pump set in the long infusion pipeline will be controlled in this step to control the flow rate of the liquid in the long infusion pipeline and avoid the occurrence of water hammer. For example: when a certain margin is determined, the speed of the switch valve is controlled, and the start and stop of the pump, the pressurization and decompression, etc. are controlled to generate corresponding constraints on the liquid in the pipeline.

[0059] Specifically, when the actual vector does not cross the hyperplane where the support vector is located, it means that the data corresponding to the current actual vector is normal data, and water hammer will not occur, so there is no need to operate the control device; when the actual vector crosses the maximum interval hyperplane, it means that water hammer is likely to occur, and the control device needs to be controlled to avoid the occurrence of water hammer. When the actual vector crosses the hyperplane where the pre-trained support vector is located, it means that water hammer may or may not occur at this time. At this time, it will be further determined whether the actual vector exceeds the expansion margin: when the actual vector does not exceed the expansion margin, it means that the data corresponding to the actual vector will be judged as normal data at this time, and water hammer will not occur. At this time, the control device will usually not be operated; when the actual vector exceeds the expansion margin, it means that the data corresponding to the actual vector will be judged as abnormal data at this time, and water hammer will occur. At this time, the control device usually needs to be operated.

[0060] S104: Detecting the actual water hammer situation corresponding to the actual vector crossing the hyperplane using a water hammer criterion.

[0061] In the embodiment of the present invention, the data generated by the flow of liquid in the long infusion pipeline to be tested will continue to be detected, and whether water hammer occurs in the actual situation will be determined according to the water hammer criterion. The specific content of the water hammer criterion can be determined according to the actual situation, and is not specifically limited here. The water hammer criterion can also be determined by the long infusion pipeline model established above.

[0062] In this step, the water hammer criterion usually leaves a little safety margin, that is, when the water hammer criterion determines that a water hammer has occurred, it may not actually have occurred, but the safety margin can effectively ensure the safe use of the long infusion line. Correspondingly, in this step, the actual water hammer situation determined is specifically whether a water hammer has occurred or not.

[0063] S105: adjusting the support vector and / or the expansion margin according to the actual water hammer situation.

[0064] In this step, the support vector and / or expansion margin will be adjusted according to the actual water hammer situation. Specifically, when the actual water hammer situation indicates that no water hammer occurs, support vector migration will be performed in this step. Specifically, when the hyperplane after the support vector plus the expansion margin is actually verified to be safe, the vector between the hyperplane constructed by the original support vector and the hyperplane after the expansion margin is added should be a new support vector, which is the migration of the support vector. Accordingly, this step specifically includes: when the actual water hammer situation is that no water hammer occurs, and the actual vector exceeds the plane corresponding to the expansion margin, the support vector is moved forward. That is, when it is judged in S103 that water hammer will occur according to the expansion margin, but water hammer does not actually occur, the support vector will be moved forward to adjust the position of the hyperplane.

[0065] When the actual water hammer situation indicates that water hammer has occurred, the above expansion margin needs to be specifically adjusted. That is, this step includes: when the actual water hammer situation indicates that water hammer has occurred, the expansion margin is adjusted. The expansion margin is adjusted based on the owner's tolerance for the safety state. For example, 10% or more of the distance between the support vector and the maximum interval plane can be set. When the value is higher, the probability of misjudgment is greater.

[0066] Specifically, this step generally includes: when the actual water hammer situation is water hammer, and the actual vector does not exceed the plane corresponding to the expansion margin, reducing the expansion margin. That is, when it is judged in S103 that water hammer will not occur according to the expansion margin, but water hammer actually occurs, indicating that the expansion margin is too large, the expansion margin can be reduced in this step to ensure the accuracy of subsequent judgment.

[0067] In an embodiment of the present invention, a maximum margin hyperplane is used as the limit of the outward expansion margin of the support vector. After exceeding the maximum margin hyperplane, it is regarded as a dangerous area, the hyperplane constructed by the support vector is regarded as a safe area, and the areas between are regarded as possible areas. By setting the margin, a test of danger is conducted to reduce the probability of misclassification.

[0068] A method for preventing water hammer in a long pipeline provided by an embodiment of the present invention can accurately determine the occurrence of water hammer by using a support vector machine to generate parameters such as a support vector according to historical actual data combined with the change law of data output by a single sensor and the correlation characteristics between output data of multiple sensors. The method adopts a combination of theory and data-driven approach to reduce the demand for data, and can update support vectors and expand margins according to actual data, can update dynamic boundaries online, can accumulate data according to actual production conditions, and autonomously expand its dynamic range.

[0069] The specific contents of the method for preventing water hammer in long pipelines provided by the present invention will be described in detail in the following embodiments of the invention.

[0070] Please refer to Figure 2 , Figure 2 The present invention provides a flow chart of a specific method for preventing water hammer in a long pipeline.

[0071] See also Figure 2 In an embodiment of the present invention, a method for preventing water hammer in a long pipeline includes:

[0072] S201: Acquire historical actual data generated by sensors distributed in the long infusion pipeline.

[0073] In this step, the historical actual data generated by the sensor in the long infusion pipeline to be tested is first obtained so as to train the support vector machine in the subsequent steps.

[0074] S202: Acquire water hammer data generated by the sensor when water hammer occurs in a simulated long infusion pipeline.

[0075] In this step, simulated water hammer data is obtained, and the specific content of the water hammer data has been described in detail in the above-mentioned embodiment of the invention, and will not be repeated here. It should be noted that this step and the above-mentioned S201 can be executed in parallel or in sequence, and no specific limitation is made here.

[0076] S203: Generate a feature vector according to historical actual data and water hammer data.

[0077] In this step, the above historical actual data and water hammer data will generate feature vectors. The specific content of generating the feature vectors can refer to the specific process of converting the actual data into the actual vectors in S102. Usually, the original high-dimensional historical actual data and water hammer data are reduced in dimension to feature vectors through dimensionality reduction processing. That is, this step can specifically include: reducing the dimension of the historical actual data and the water hammer data to generate the feature vectors. The specific content will not be repeated here. In this step, the historical actual data and the water hammer data are converted into feature vectors to facilitate the training of the support vector machine.

[0078] Specifically, before this step, it is usually necessary to perform noise reduction on the historical actual data and the water hammer data to ensure the accuracy of subsequent calculations. The specific process of noise reduction can be referred to the prior art and will not be described in detail here.

[0079] S204: calling a support vector machine to determine a support vector, a hyperplane, and a maximum margin hyperplane according to the feature vector.

[0080] In this step, the support vector machine is called to determine the initial support vector, hyperplane and maximum margin hyperplane according to the above eigenvector for the first use in the subsequent process.

[0081] S205: Acquire actual data generated in real time by sensors distributed in the long infusion pipeline.

[0082] S206: Convert the actual data into an actual vector.

[0083] S207: When the actual vector crosses the hyperplane where the pre-trained support vector is located, the control device of the long infusion pipeline is controlled based on the pre-set expansion margin.

[0084] S208: Detecting the actual water hammer situation corresponding to the actual vector crossing the hyperplane using a water hammer criterion.

[0085] S209: adjusting the support vector and / or the expansion margin according to the actual water hammer situation.

[0086] The above S205 to S209 are basically the same as S101 to S105 in the above invention embodiment. Please refer to the above invention embodiment for details, which will not be repeated here.

[0087] A method for preventing water hammer in a long pipeline provided by an embodiment of the present invention can accurately determine the occurrence of water hammer by using a support vector machine to generate parameters such as a support vector according to historical actual data combined with the change law of data output by a single sensor and the correlation characteristics between output data of multiple sensors. The method adopts a combination of theory and data-driven approach to reduce the demand for data, and can update support vectors and expand margins according to actual data, can update dynamic boundaries online, can accumulate data according to actual production conditions, and autonomously expand its dynamic range.

[0088] A device for preventing water hammer in a long pipeline provided by an embodiment of the present invention is introduced below. The device for preventing water hammer in a long pipeline described below and the method for preventing water hammer in a long pipeline described above can be referred to each other.

[0089] Figure 3 A structural block diagram of a device for preventing water hammer in a long pipeline provided by an embodiment of the present invention, referring to Figure 3 , devices to prevent water hammer in long pipelines may include:

[0090] The actual data acquisition module 100 is used to acquire the actual data generated in real time by sensors distributed in the long infusion pipeline.

[0091] The conversion module 200 is used to convert the actual data into an actual vector.

[0092] The control module 300 is used to control the control device of the long infusion pipeline based on a preset expansion margin when the actual vector crosses the hyperplane where the pre-trained support vector is located; the support vector is a support vector pre-determined by a support vector machine based on historical actual data and water hammer data; the water hammer data includes the change law of a single sensor output data and the correlation characteristics between multiple sensor output data; the hyperplane corresponds to the support vector, and the maximum value of the expansion margin corresponds to the maximum interval hyperplane corresponding to the support vector.

[0093] The criterion detection module 400 is used to detect the actual water hammer situation corresponding to the actual vector crossing the hyperplane through the water hammer criterion.

[0094] The adjustment module 500 is used to adjust the support vector and / or the expansion margin according to the actual water hammer situation.

[0095] Preferably, in the embodiment of the present invention, the adjustment module 500 is specifically used for:

[0096] When the actual water hammer situation is that no water hammer occurs and the actual vector exceeds the plane corresponding to the expansion margin, the support vector is moved forward.

[0097] Preferably, in the embodiment of the present invention, the adjustment module 500 is specifically used for:

[0098] When the actual water hammer situation is water hammer occurring, the expansion margin is adjusted.

[0099] Preferably, in the embodiment of the present invention, the adjustment module 500 is specifically used for:

[0100] When the actual water hammer situation is water hammer, and the actual vector does not exceed the plane corresponding to the expansion margin, the expansion margin is reduced.

[0101] Preferably, in the embodiment of the present invention, it also includes:

[0102] The historical data acquisition module is used to obtain the historical actual data generated by the sensors distributed in the long infusion pipeline.

[0103] The simulation module is used to obtain water hammer data generated by the sensor when simulating water hammer occurring in the long infusion pipeline.

[0104] A feature vector module is used to generate a feature vector according to the historical actual data and the water hammer data.

[0105] The initial support vector machine module is used to call the support vector machine to determine the support vector, the hyperplane and the maximum margin hyperplane according to the feature vector.

[0106] Preferably, in the embodiment of the present invention, the feature vector module is specifically used for:

[0107] The dimension of the historical actual data and the water hammer data is reduced to generate the feature vector.

[0108] Preferably, in the embodiment of the present invention, it also includes:

[0109] A noise reduction module is used to reduce noise on the historical actual data and the water hammer data.

[0110] The device for preventing water hammer in a long pipeline of the present embodiment is used to implement the aforementioned method for preventing water hammer in a long pipeline. Therefore, the specific implementation of the device for preventing water hammer in a long pipeline can be seen in the embodiment of the method for preventing water hammer in a long pipeline in the preceding text. For example, the actual data acquisition module 100, the conversion module 200, the control module 300, the criterion detection module 400, and the adjustment module 500 are respectively used to implement steps S101 to S105 in the aforementioned method for preventing water hammer in a long pipeline. Therefore, its specific implementation can refer to the description of the corresponding embodiments of each part, which will not be repeated here.

[0111] A device for preventing water hammer in a long pipeline provided in an embodiment of the present invention is introduced below. The device for preventing water hammer in a long pipeline described below and the method for preventing water hammer in a long pipeline and the device for preventing water hammer in a long pipeline described above can be referred to each other.

[0112] Please refer to Figure 4 , Figure 4 A structural block diagram of a device for preventing water hammer in a long pipeline provided by an embodiment of the present invention.

[0113] Reference Figure 4 The device for preventing water hammer in a long pipeline may include a processor 11 and a memory 12 .

[0114] The memory 12 is used to store computer programs; the processor 11 is used to implement the method for preventing water hammer in long pipelines described in the above-mentioned embodiment of the invention when executing the computer program.

[0115] The processor 11 in the device for preventing water hammer in a long pipeline of this embodiment is used to install the device for preventing water hammer in a long pipeline described in the above-mentioned invention embodiment, and the processor 11 combined with the memory 12 can implement the method for preventing water hammer in a long pipeline described in any of the above-mentioned invention embodiments. Therefore, the specific implementation of the device for preventing water hammer in a long pipeline can be seen in the embodiment of the method for preventing water hammer in a long pipeline in the above text, and its specific implementation can refer to the description of the corresponding embodiments of each part, which will not be repeated here.

[0116] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, a method for preventing water hammer in a long pipeline introduced in any of the above-mentioned embodiments of the invention is implemented. The rest of the content can refer to the prior art and will not be described in detail here.

[0117] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0118] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0119] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0120] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0121] The above is a detailed introduction to a method for preventing water hammer in a long pipeline, a device for preventing water hammer in a long pipeline, a device for preventing water hammer in a long pipeline, and a computer-readable storage medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present invention, the present invention can also be improved and modified in a number of ways, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

Claims

1. A method for preventing water hammer in a long pipeline, characterized in that: include: Obtain the actual data generated in real time by sensors distributed in long infusion pipelines; Converting the actual data into an actual vector; The position of the actual vector and the distance between each hyperplane reflect the probability of water hammer; When the actual vector crosses the hyperplane where the pre-trained support vector is located, the control device of the long infusion pipeline is controlled according to the pre-set expansion margin; the support vector is a support vector determined in advance by a support vector machine based on historical actual data and water hammer data; the water hammer data includes the change law of a single sensor output data and the correlation characteristics between multiple sensor output data; the hyperplane corresponds to the support vector, and the maximum value of the expansion margin corresponds to the maximum interval hyperplane corresponding to the support vector; after exceeding the maximum interval hyperplane, it is regarded as a dangerous area, and the area within the hyperplane is regarded as a safe area; Detecting the actual water hammer situation corresponding to the actual vector crossing the hyperplane by using a water hammer criterion; The support vector and / or the expansion margin are adjusted according to the actual water hammer situation.

2. The method according to claim 1, characterized in that The adjusting the support vector and / or the expansion margin according to the actual water hammer situation includes: When the actual water hammer situation is that no water hammer occurs and the actual vector exceeds the plane corresponding to the expansion margin, the support vector is moved forward.

3. The method according to claim 2, characterized in that The adjusting the support vector and / or the expansion margin according to the actual water hammer situation includes: When the actual water hammer situation is water hammer occurring, the expansion margin is adjusted.

4. The method according to claim 3, characterized in that When the actual water hammer situation is water hammer, adjusting the expansion margin includes: When the actual water hammer situation is water hammer, and the actual vector does not exceed the plane corresponding to the expansion margin, the expansion margin is reduced.

5. The method according to claim 1, characterized in that: Also includes: Obtain historical actual data generated by sensors distributed in long infusion pipelines; Acquire water hammer data generated by the sensor when simulating water hammer occurring in the long infusion pipeline; Generate a feature vector according to the historical actual data and the water hammer data; A support vector machine is called to determine the support vector, the hyperplane and the maximum margin hyperplane according to the feature vector.

6. The method according to claim 5, characterized in that The generating of the feature vector according to the historical actual data and the water hammer data comprises: The dimension of the historical actual data and the water hammer data is reduced to generate the feature vector.

7. The method according to claim 6, characterized in that Before generating a feature vector according to the historical actual data and the water hammer data, the method further includes: Noise reduction is performed on the historical actual data and the water hammer data.

8. A device for preventing water hammer in a long pipeline, characterized in that: include: The actual data acquisition module is used to acquire the actual data generated in real time by sensors distributed in the long infusion pipeline; A conversion module, used for converting the actual data into an actual vector; the position of the actual vector and the distance of each hyperplane reflect the probability of water hammer; A control module, used for controlling the control device of the long infusion pipeline according to a preset expansion margin when the actual vector crosses the hyperplane where the pre-trained support vector is located; the support vector is a support vector pre-determined by a support vector machine according to historical actual data and water hammer data; the water hammer data includes the variation law of a single sensor output data and the correlation characteristics between multiple sensor output data; the hyperplane corresponds to the support vector, and the maximum value of the expansion margin corresponds to the maximum interval hyperplane corresponding to the support vector; after exceeding the maximum interval hyperplane, it is regarded as a dangerous area, and the area within the hyperplane is regarded as a safe area; A criterion detection module, used for detecting the actual water hammer situation corresponding to the actual vector crossing the hyperplane by using the water hammer criterion; An adjustment module is used to adjust the support vector and / or the expansion margin according to the actual water hammer situation.

9. A device for preventing water hammer in a long pipeline, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the method for preventing water hammer in a long pipeline as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for preventing water hammer in a long pipeline as claimed in any one of claims 1 to 7 are implemented.

Images