Pump set type selection method based on actual working condition delay simulation and storage medium

Abstract

The invention discloses a pump set model selection method based on actual working condition delay simulation and a storage medium, and the model selection method takes actual operation historical boundary data of a pump room to be transformed as a basis of pump set design, and breaks away from a traditional single working condition design situation, so that the selected pump set is closer to an actual operation working condition. And the optimal frequency combination meeting the working conditions and the corresponding operation power serve as the calculation basis of future operation of the pump set, the expected saving cost is calculated through long-time-period simulation, and the appropriate water pump model number combination is selected. Compared with the existing technical scheme, the model selection method provided by the scheme not only can meet the standard design requirement, but also ensures that the pump set operates as efficiently as possible under the daily condition.

Description

Technical Field

[0001] This invention relates to the field of water supply and drainage equipment, and in particular to a pump set selection method and storage medium based on time-delay simulation of actual working conditions. Background Technology

[0002] In traditional pump set selection and design, pumps are generally selected based on the maximum design flow rate that may be encountered during operation, according to design specifications and water consumption quotas and probability formulas. However, water consumption quotas and water consumption probabilities do not necessarily match actual operating conditions. According to previous research and actual operating conditions, the probability of the design operating conditions occurring is often only one in ten thousand, or even less than one in ten thousand, leading to the selection of pumps that are generally too large, resulting in pumps operating in the inefficient range for a large portion of daily operation. Summary of the Invention

[0003] Therefore, it is necessary to provide a pump set selection method and storage medium based on actual working condition delay simulation to solve the problem that traditional pump set selection is based on the maximum working condition, which deviates greatly from the actual daily operating conditions, resulting in low daily operating efficiency.

[0004] To achieve the above objectives, the inventors provide a pump set selection method based on actual operating condition time-delay simulation, comprising the following steps:

[0005] S1: Obtain a sample set of historical data for the pump station. :

[0006]

[0007] In the formula, This represents the head of the pump unit at time t. This represents the flow rate of the pump unit at time t;

[0008] S2: Based on the sample set Obtain the distribution model of head X and flow rate Y, and determine the value range of head X and flow rate Y;

[0009] S3: Establish a database of candidate pump sets, including each candidate pump and its mapping relationship with flow rate, head, and speed:

[0010]

[0011] In the formula, The operating flow rate of the water pump with model number i; The operating head of the water pump with model number i is represented by its name. The rotational speed of the water pump with model number i;

[0012] S4: Based on the distribution model of head X and flow rate Y constructed in step S2, determine the range of values ​​for head X. The mapping relationship between the head and speed of each candidate pump was selected from the database of candidate pump sets. Zhongyangcheng The domain includes The water pumps, and then construct a set of alternative water pumps M;

[0013] S5: Construct a set of alternative water pump model combinations C based on the alternative water pump set M. The set of alternative water pump model combinations C includes combinations of different water pump models required by the user.

[0014] S6: Based on the sample set Traffic in The range of values ​​is used to obtain the required number of each pump model in the set of candidate pump model combinations C, thus obtaining a feasible combination of pump model numbers.

[0015] S7: Calculate the expected cost savings for each possible combination of pump models;

[0016] S8: Output the number of feasible pump models that meet the requirements based on the expected cost savings.

[0017] Furthermore, in step S7, the expected cost savings are obtained by subtracting the estimated energy consumption during the design period from the historical actual operating energy consumption of the pump house.

[0018] Furthermore, in step S2, the distribution model includes the joint probability density function. The range of values ​​for X and Y is 1. ;

[0019] In step S3, the candidate pump group database includes the mapping relationship between the operating power, speed, and flow rate of each candidate pump. ;

[0020] Step S7 includes the following steps:

[0021] Targeting the satisfaction any operating point Determine if there are feasible speed values ​​for each pump. This ensures that the total flow rate provided by the combination of pump models satisfies the mass conservation equation constraint requirements:

[0022]

[0023] In the formula, This represents the i-th pump in the pump set being processed at the specified head. With rotational speed The output flow rate is below. Indicates the total number of water pumps;

[0024] If so, the cost minimization function is obtained according to the following formula:

[0025]

[0026] In the formula, Represents the unit price of electricity. Representing the sampling frequency, in the process of solving the above-mentioned cost minimization function, the feasible speed values ​​of each pump should meet the requirements of the mass conservation equation;

[0027] Based on the joint probability density function and the cost minimization function, the arbitrary value after replacing the water pump is obtained. Expected energy costs for the time period:

[0028]

[0029] The estimated energy cost during the design period is obtained based on the expected energy cost after replacing the water pump:

[0030] .

[0031] Furthermore, in step S2, the two-dimensional probability distribution model includes a discrete distribution law. ;

[0032] In the formula, The range of values ​​is , The domain of the distribution of the two-dimensional discrete variable;

[0033] In step S3, the candidate pump group database includes the mapping relationship between the operating power, speed, and flow rate of each candidate pump. ;

[0034] Step S7 includes the following steps:

[0035] For any operating point within the domain of the discrete distribution law of a two-dimensional discrete variable distribution. Determine if there are feasible speed values ​​for each pump. This ensures that the total flow rate provided by the combination of pump models satisfies the mass conservation equation constraint requirements:

[0036]

[0037] In the formula, This represents the i-th pump in the pump set being processed at the specified head. With rotational speed The output flow rate is below. Indicates the total number of water pumps;

[0038] If so, the cost minimization function is obtained according to the following formula:

[0039]

[0040] In the formula, Represents the unit price of electricity. Representing the sampling frequency, in the process of solving the above-mentioned cost minimization function, the feasible speed values ​​of each pump should meet the requirements of the mass conservation equation;

[0041] Based on the discrete distribution law and minimizing the cost function, the expected energy consumption cost for any time period ∆t after replacing the water pump is obtained:

[0042]

[0043] The estimated energy cost within the design period t is obtained based on the expected energy cost after replacing the water pump:

[0044] .

[0045] Furthermore, in step S3, the candidate pump group database includes the mapping relationship between the operating power, speed, and flow rate of each candidate pump. ;

[0046] Step S7 includes the following steps:

[0047] Based on sample set The sample set is processed as an equally weighted discrete model. any working point in Determine if there are feasible speed values ​​for each pump. This ensures that the total flow rate provided by the combination of pump models satisfies the mass conservation equation constraint requirements:

[0048]

[0049] In the formula, This represents the i-th pump in the pump set being processed at the specified head. With rotational speed The output flow rate is below. Indicates the total number of water pumps;

[0050] If so, the cost minimization function is obtained according to the following formula:

[0051]

[0052] In the formula, Represents the unit price of electricity. Representing the sampling frequency, in the process of solving the above-mentioned cost minimization function, the feasible speed values ​​of each pump should meet the requirements of the mass conservation equation;

[0053] Based on the sample set And minimizing the cost function to obtain the design period Expected energy costs within:

[0054] ;

[0055] In the formula, For sample set The length.

[0056] Furthermore, it also includes the following steps:

[0057] Determine the electricity unit price Is it time-of-use pricing? If so, then introduce the time dimension when constructing the distributed model. and the electricity unit price Replace with time-of-use electricity price This is used to minimize the cost function and calculate the expected energy consumption cost.

[0058] Further, step S6 includes the following steps:

[0059] For each pump model combination in the candidate pump combination set C, determine all feasible combinations of the number of pumps; wherein, feasible combinations of the number of pumps are generated in the following manner:

[0060] In the set of candidate pump model combinations C, pumps of preset initial models are added incrementally, starting with a single pump. After each addition, the model is determined based on the sample set. Traffic in Determine the minimum number of pumps required for other models within the given range, and repeat the above process until the initial set of pumps can meet the sample set requirements. Traffic in The requirement is met until no other type of water pump is needed.

[0061] Furthermore, in step S1, the sample set of historical data of the pump station It can be obtained through the following steps:

[0062] The historical outflow, outlet pressure, and inlet pressure of the pump station are obtained for measurement.

[0063] The sample set is obtained after processing the data based on outflow, outlet pressure, and inlet pressure. .

[0064] Furthermore, step S8 includes the following steps:

[0065] Sort and output all feasible combinations of pump models based on the expected cost savings; or:

[0066] Obtain the purchase price of each pump in all feasible combinations of pump models. Calculate the payback period based on the pump purchase price and expected cost savings. Sort all feasible combinations of pump models according to their payback periods and output the results.

[0067] To achieve the above objectives, the inventors also provide a storage medium storing a computer program, which, when executed by a processor, performs the pump selection method described in any of the above embodiments.

[0068] Unlike existing technologies, the above technical solution uses the actual operating history boundary data of the pump station to be modified as the basis for pump set design, departing from the traditional single-condition design scenario and making the selected pump set closer to actual operating conditions. The optimal frequency combination and its corresponding operating power under the operating conditions are used as the basis for calculating the future operation of the pump set. Through long-term simulation calculations of expected cost savings, a suitable combination of pump models and numbers is selected. Compared with existing technical solutions, the selection method proposed in this solution not only meets the standard design requirements but also ensures that the pump set operates as efficiently as possible under normal conditions.

[0069] The above description of the invention is merely an overview of the technical solution of this application. In order to enable those skilled in the art to better understand the technical solution of this application and to implement it based on the description and drawings, and to make the above-mentioned objectives and other objectives, features and advantages of this application easier to understand, the following description is provided in conjunction with the specific embodiments and drawings of this application. Attached Figure Description

[0070] The accompanying drawings are only used to illustrate the principles, implementation methods, applications, features, and effects of specific embodiments of the present invention and other related contents, and should not be considered as limitations on this application.

[0071] Figure 1 This is a flowchart illustrating the pump set selection method of this application;

[0072] Figure 2 This is a flowchart of step S7 in Embodiment 1 of this application;

[0073] Figure 3 This is a flowchart of step S7 in Embodiment 2 of this application;

[0074] Figure 4 This is a flowchart of step S1 of this application. Detailed Implementation

[0075] To illustrate the possible application scenarios, technical principles, implementable specific solutions, and achievable objectives and effects of this application in detail, the following description, in conjunction with the listed specific embodiments and accompanying drawings, provides a detailed explanation. The embodiments described herein are merely illustrative of the technical solutions of this application and are therefore intended to limit the scope of protection of this application.

[0076] In this document, the term "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The term "embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment, nor does it specifically limit its independence or connection with other embodiments. In principle, in this application, as long as there are no technical contradictions or conflicts, the technical features mentioned in each embodiment can be combined in any way to form corresponding implementable technical solutions.

[0077] Unless otherwise defined, the technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the use of related terms herein is merely for the purpose of describing particular embodiments and is not intended to limit this application.

[0078] In the description of this application, the term "and / or" is used to describe the logical relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A exists, B exists, and A and B exist simultaneously. Additionally, the character " / " in this document generally indicates that the preceding and following objects have an "or" logical relationship.

[0079] In this application, terms such as “first” and “second” are used only to distinguish one entity or operation from another, and do not necessarily require or imply any actual quantity, hierarchy or order relationship between these entities or operations.

[0080] Unless otherwise specified, the use of terms such as “comprising,” “including,” “having,” or other similar expressions in this application is intended to cover non-exclusive inclusion, which does not exclude the presence of additional elements in a process, method, or product that includes the stated elements, such that a process, method, or product that includes a list of elements may include not only those defined elements but also other elements not expressly listed, or elements inherent to such a process, method, or product.

[0081] As understood in the Examination Guidelines, in this application, expressions such as "greater than," "less than," and "exceeding" are understood to exclude the stated number; expressions such as "above," "below," and "within" are understood to include the stated number. Furthermore, in the description of the embodiments in this application, "multiple" means two or more (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups" and "multiple times," unless otherwise explicitly specified.

[0082] In the description of the embodiments of this application, the space-related expressions used, such as "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "vertical," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential," indicate the orientation or positional relationship based on the orientation or positional relationship shown in the specific embodiments or drawings. They are only for the purpose of describing the specific embodiments of this application or for the reader's understanding, and do not indicate or imply that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0083] Unless otherwise expressly specified or limited, the terms "installation," "connection," "linking," "fixing," and "setting," as used in the description of the embodiments of this application, should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two components or the interaction between two components. For those skilled in the art to which this application pertains, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0084] The processor described in the embodiments of this application can be implemented by hardware, firmware, software, or a combination thereof. It can be a circuit, one or more of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field-programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, or a microprocessor. It also includes other physical, biological, or chemical structures that can implement the same or equivalent functions as the processors listed above, such as biological neurons, quantum computing units, DNA computing units, etc., so that the processor can execute some or all of the steps in the computer program or method involved in the various embodiments of this application, or any combination of the steps mentioned therein.

[0085] The computer program involved in the embodiments can be stored in a computer device readable storage medium, which includes, but is not limited to, disks, magnetic tapes, magnetic cards, floppy disks, flash memory, optical disks, optical cards, read-only memory (ROM), random access memory (RAM), erasable programmable ROM (EPROM), and electrically erasable programmable ROM (EEPROM), etc., and also includes other biological, physical, or chemical structures that can achieve the same or equivalent functions as the storage media listed above, such as DNA, RNA, proteins, and other units with information storage capabilities. In specific embodiments, the storage medium involved can be one of the above-mentioned media types, or a combination of the above-mentioned media types. In different embodiments, the computer program involved in the embodiments can be centrally stored in a single medium, or distributed and stored in multiple media. The memory containing the computer device readable storage medium can be non-volatile memory or random access memory. These computer device readable storage media can be built into the device, or can be connected to the device involved in the embodiments as an external device or part of an external device. In some embodiments, the memory having a computer device readable storage medium is deployed locally; in other embodiments, the memory may be deployed remotely from the processor, for example, as a network-attached memory accessed via RF circuitry or an external port and a communication network, wherein the communication network may be the Internet, one or more intranets, a local area network (LAN), a wide area network (WLAN), a storage area network (SAN), or a suitable combination thereof, as long as computer device access to the memory is enabled. Furthermore, the computer program involved in the embodiments may be stored in plaintext / ciphertext form, or it may be designed as training data, integrated and recombined through model training and implicitly stored in the parameter states of a deep neural network or other machine learning model.

[0086] Please see Figure 1 This embodiment provides a pump set selection method based on actual working condition delay simulation, including the following steps:

[0087] S1: Obtain a sample set of historical data for the pump station. :

[0088]

[0089] In the formula, The pump head at time t (unit: m) represents the pump unit's head. The flow rate of the pump unit at time t (unit: m³) 3 / h);

[0090] S2: Based on the sample set Obtain the distribution model of head X and flow rate Y, and determine the range of values ​​for head X and flow rate Y;

[0091] S3: Establish a database of candidate pump sets, including each candidate pump and its mapping relationship with flow rate, head, and speed:

[0092]

[0093] In the formula, The operating flow rate of the water pump with model number i; The operating head of the water pump with model number i is represented by its name. The rotational speed of the water pump with model number i;

[0094] S4: Based on the distribution model of head X and flow rate Y constructed in step S2, determine the head. The range of values The mapping relationship between the head and speed of each candidate pump was selected from the database of candidate pump sets. Zhongyangcheng The domain includes The water pumps, and then construct a set of alternative water pumps M;

[0095] S5: Construct a set of alternative water pump model combinations C based on the alternative water pump set M. The set of alternative water pump model combinations C includes combinations of different water pump models required by the user.

[0096] S6: Based on the sample set Traffic in The range of values ​​is used to obtain the required number of each pump model in the set of candidate pump model combinations C, thus obtaining a feasible combination of pump model numbers.

[0097] S7: Calculate the expected cost savings for each possible combination of pump models;

[0098] S8: Output the number of feasible pump models that meet the requirements based on the expected cost savings.

[0099] Existing design schemes only consider the maximum operating flow rate specified in the standard design. However, research shows that the probability of this maximum operating flow rate occurring in actual operation is often less than one in ten thousand. Simply designing according to meeting the maximum operating flow rate specified in the standard will lead to the selection of an oversized pump unit, resulting in long-term operation in the inefficient range.

[0100] The main technical concept of this application lies in using the actual historical boundary data of the pump house to be modified as the basis for pump set design, departing from the traditional single-condition design scenario, and making the selected pump set closer to the actual operating conditions. The optimal frequency combination and its corresponding operating power under the operating conditions are used as the basis for calculating the future operation of the pump set. Through long-term simulation calculations of expected cost savings, a suitable combination of pump models and numbers is selected. Compared with existing technical solutions, the selection method proposed in this application not only meets the design requirements of local standards and specifications, but also ensures that the pump set operates as efficiently as possible under normal conditions.

[0101] In some embodiments, in step S7, the expected cost savings are obtained by subtracting the estimated energy consumption during the design period from the historical actual operating energy consumption of the pump house.

[0102] The estimated energy consumption cost during the design period is calculated using a distributed model; however, the estimated energy consumption cost will vary depending on the distributed model used. The following sections describe different implementation methods.

[0103] Please see Figure 2 In Implementation Method 1, in step S2, the distribution model includes a joint probability density function. ,in , The range of values ​​is ;

[0104] In step S3, the candidate pump group database includes the mapping relationship between the operating power, speed, and flow rate of each candidate pump. ;

[0105] Step S7 includes the following steps:

[0106] against any operating point Determine if there are feasible speed values ​​for each pump. This ensures that the total flow rate provided by the combination of pump models satisfies the mass conservation equation constraint requirements:

[0107]

[0108] In the formula, This represents the i-th pump in the pump set being processed at the specified head. With rotational speed The output flow rate is below. Indicates the total number of water pumps;

[0109] If so, the cost minimization function is obtained according to the following formula:

[0110]

[0111] In the formula, Represents the unit price of electricity. Representing the sampling frequency, in the process of solving the above-mentioned cost minimization function, the feasible speed values ​​of each pump should meet the requirements of the mass conservation equation;

[0112] Based on the joint probability density function and the cost minimization function, the arbitrary value after replacing the water pump is obtained. Expected energy costs for the time period:

[0113]

[0114] The estimated energy cost during the design period is obtained based on the expected energy cost after replacing the water pump:

[0115] .

[0116] Please see Figure 3 In the second implementation method, in step S2, the two-dimensional probability distribution model includes a discrete distribution law. In the formula, The range of values ​​is , Let be the domain of the distribution of the two-dimensional discrete variables. The joint probability distribution can be obtained by analyzing the sample set. The two-dimensional space is binned to transform continuous variables into discrete random variables, resulting in discrete probability distributions, and then the variables are determined. , Domain range .

[0117] In step S3, the candidate pump group database includes the mapping relationship between the operating power, speed, and flow rate of each candidate pump (including its matching motor). ;

[0118] Step S7 includes the following steps:

[0119] For the domain of the discrete distribution law in the two-dimensional discrete variable distribution Any operating point within Determine if there are feasible speed values ​​for each pump. This ensures that the total flow rate provided by the combination of pump models satisfies the mass conservation equation constraint requirements:

[0120]

[0121] In the formula, This represents the i-th pump in the pump set being processed at the specified head. With rotational speed The output flow rate is below. Indicates the total number of water pumps;

[0122] If so, the cost minimization function is obtained according to the following formula:

[0123]

[0124] In the formula, Represents the unit price of electricity. Representing the sampling frequency, in the process of solving the above-mentioned cost minimization function, the feasible speed values ​​of each pump should meet the requirements of the mass conservation equation;

[0125] Based on the discrete distribution law and minimizing the cost function, any value obtained after replacing the water pump... Expected energy costs for the time period:

[0126]

[0127] The estimated energy cost within the design period t is obtained based on the expected energy cost after replacing the water pump:

[0128] .

[0129] The difference between Implementation Method 1 and Implementation Method 2 lies in the type of distribution model used: Implementation Method 1 uses a joint probability density function as the distribution model and calculates the expected energy consumption cost after replacing the water pump based on this function and the cost minimization function; Implementation Method 2 uses a discrete distribution law as the distribution model and calculates the corresponding expected energy consumption cost based on this distribution law and the cost minimization function.

[0130] In Implementation Method 3, a technical concept different from Implementation Methods 1 and 2 is presented. Implementation Method 3 is based on a sample set. The expected energy consumption cost is calculated by combining the minimum cost function.

[0131] In step S3, the candidate pump group database includes the mapping relationship between the operating power, speed, and flow rate of each candidate pump. ;

[0132] Step S7 includes the following steps:

[0133] Based on sample set The sample set is processed as an equally weighted discrete model. any working point in Determine if there are feasible speed values ​​for each pump. This ensures that the total flow rate provided by the combination of pump models satisfies the mass conservation equation constraint requirements:

[0134]

[0135] In the formula, This represents the i-th pump in the pump set being processed at the specified head. With rotational speed The output flow rate is below. Indicates the total number of water pumps;

[0136] If so, the cost minimization function is obtained according to the following formula:

[0137]

[0138] In the formula, Represents the unit price of electricity. Representing the sampling frequency, in the process of solving the above-mentioned cost minimization function, the feasible speed values ​​of each pump should meet the requirements of the mass conservation equation;

[0139] Based on the sample set And minimizing the cost function to obtain the design period Expected energy costs within:

[0140] ;

[0141] In the formula, For sample set The length.

[0142] It should be noted that the above calculation process for expected energy costs is based on the assumption that the pumping station uses a constant electricity price; when the pumping station uses time-of-use pricing, the following steps are also included:

[0143] Determine the electricity unit price based on the type of electricity used in the pump room. If it is time-based pricing, then add the dimension of the time period to which the sample belongs to the sample set. ,at this time Furthermore, a time dimension is introduced when constructing the distribution model. and the electricity unit price Replace with Time-of-use electricity price This is used to minimize the cost function and calculate the expected energy consumption cost.

[0144] In Implementation Method 1, if the pumping station uses time-of-use pricing power, then the time-of-use data is considered when calculating the joint probability density function of the two-dimensional variables X and Y. Calculate each time period Below is the joint probability density function of two-dimensional variables X and Y. and the electricity unit price Replace with time-of-use pricing The cost function is minimized as follows:

[0145]

[0146] During time interval h, any The average expected energy cost for the time period is:

[0147]

[0148] The estimated energy cost during the design period t is obtained based on the expected energy cost after replacing the water pump:

[0149] .

[0150] In implementation method two, if the pumping station uses time-of-use pricing power, then time is considered when calculating the joint distribution law of the two-dimensional variables X and Y. Replace it with the joint distribution law of three-dimensional variables X, Y, and H, and change the electricity unit price. Replace with time-of-use pricing The cost function is minimized in the same way as in Implementation Method 1. During the time period, any The expected energy cost for the time period is:

[0151]

[0152] The estimated energy cost within the design period t is obtained based on the expected energy cost after replacing the water pump:

[0153] .

[0154] In implementation method three, the cost function is minimized in the same way as in implementation method one. If the pumping station uses time-of-use pricing power, the expected energy consumption cost within the design period t is:

[0155]

[0156] In some embodiments, step S6 includes the following steps:

[0157] For each pump model combination in the candidate pump combination set C, determine all feasible combinations of the number of pumps; wherein, feasible combinations of the number of pumps are generated in the following manner:

[0158] In the set of candidate pump model combinations C, pumps of preset initial models are added incrementally, starting with a single pump. After each addition, the model is determined based on the sample set. Traffic in Determine the minimum number of pumps required for other models within the given range, and repeat the above process until the initial set of pumps can meet the sample set requirements. Traffic in The upper limit is reached, and no other type of water pump is needed.

[0159] The process iterates through each pump model combination in the candidate pump combination set C. Assuming a certain pump model combination contains pumps of models A and B, the calculation process is illustrated in the example below (the same applies to more pump model combinations):

[0160] Determine all possible combinations of pump numbers. For each type combination, start with 1 pump and gradually increase the number. For example, after determining 'a' type A pumps, find the minimum number of type B pumps that can satisfy the range of values ​​for y in the sample set S, forming a pump combination to be used. Subsequently, gradually increase the number of type A pumps and determine the number of type B pumps according to the same logic, until multiple type A pumps can meet the requirements and no more type B pumps are needed, then stop.

[0161] Please see Figure 4 In some embodiments, in step S1, the sample set of historical data of the pump station It can be obtained through the following steps:

[0162] The pump station's historical outflow, outlet pressure (water level), and inlet pressure (water level) are used for measurement.

[0163] Calculate the absolute head at the outlet and inlet by combining the installation height and measurement unit of the inlet and outlet pressure gauges or water level gauges;

[0164] Subtract the absolute head at the outlet from the absolute head at the same moment to obtain the head at that moment, and pair it with the flow rate to form a sample pair;

[0165] The sample set was obtained after data cleaning and processing based on outflow, outlet pressure, and inlet pressure. .

[0166] sampling frequency of the metering process The sampling time is less than 1 hour. Preferably, a data sampling frequency of 1 minute or 5 minutes is used. For pump stations already equipped with relevant sensors, the existing equipment can be used directly for measurement, and historical measurement data can be obtained. For pump stations without sensors, measurements are taken by installing clamp-on flow meters, temporary pressure measuring devices, and water level measuring devices. After the above measurements, and after data cleaning (including cleaning the data at the same time using the 3σ method, box plot method, etc., and static threshold judgment conditions), a sample set of historical data for the pump station can be obtained. .

[0167] In some embodiments, step S8 includes the following steps:

[0168] Sort and output all feasible combinations of pump models based on the expected cost savings. When outputting, you can choose to output the feasible combination with the largest expected cost savings, the top three optimal combinations, or all feasible combinations.

[0169] Alternatively, in some other embodiments, step S8 includes the following steps:

[0170] Obtain the purchase price of each pump in all feasible combinations of pump models. Based on the pump purchase price and expected cost savings, calculate the payback period. Sort all feasible combinations of pump models according to their payback periods and output the results. When outputting, you can choose the feasible combination with the shortest payback period, output the top three optimal combinations, or output all feasible combinations.

[0171] Specifically, if the water pump purchase price exists in the database, the installation cost of the water pump will be included. +Water pump purchase price As a one-time investment, the expected annual savings will be... (The energy cost saved by using the new pump set compared to the old pump set in that year) is used as a return to calculate the investment payback period, and the pumps are sorted by investment payback period.

[0172] The formula for calculating the static payback period is as follows:

[0173]

[0174] As an equivalent alternative to the static payback period, the dynamic payback period can also be determined based on the year in which the cumulative present value turns from negative to positive according to the annual cash flows, and then sorted by dynamic payback period.

[0175] The above scheme can intuitively reflect the economic return rate of different pump set configuration schemes. This scheme comparison method based on investment payback period can better adapt to the current investment decision requirements of owners.

[0176] The pump set selection method is introduced here:

[0177] 1. For pump sets requiring upgrades, the pump set's flow rate, outlet pressure (water level), and inlet pressure (water level) are measured. During the measurement process, the data sampling frequency should not exceed 1 hour; in this embodiment, a data sampling frequency of 1 minute and 5 minutes is used. For pump rooms already equipped with relevant sensors, the existing equipment can be used directly for measurement, and historical measurement data can be obtained; for pump rooms not originally equipped with sensors, measurements are performed by installing clamp-on flow meters, temporary pressure measuring devices, and water level measuring devices.

[0178] 2. After the above measurements are performed, and after data cleaning (including cleaning the data at the same time using the 3σ method, box plot method, etc., and static threshold judgment conditions), a sample set of historical data of the pump station can be obtained. , denoted as:

[0179]

[0180] 3. Based on the sample set Calculate the joint probability density function of two-dimensional variables X and Y. And in this process, determine the range of values ​​for the two-dimensional variables. Alternatively, it can be done by analyzing the sample set. Two-dimensional spatial binning transforms continuous variables into discrete random variables, yielding... joint distribution law And determine the domain of the variable; or directly based on the sample set. Construct an equal-weight discrete random variable model.

[0181] 4. Establish a database of candidate pump sets, including price data for each pump; maximum and minimum pump speeds (or maximum and minimum frequencies under variable frequency operation); and the mapping relationship between pump flow rate, speed, and head. The mapping relationship between the operating power of water pump i (including its matching motor) and its speed and flow rate. Where n represents rotational speed, or frequency can be used instead. The above mapping relationship can be established in the following ways: (1) by directly processing the theoretical function; (2) by fitting the sample data; and (3) by actual measurement and processing with fitting or interpolation.

[0182] 5. According to the distribution model The range of values, combined with middle The domain of definition is used to determine suitable alternative water pumps, with the following requirements: middle The domain should include the distribution model. The range of values ​​for is given, thus providing the alternative pump set M.

[0183] 6. In the alternative pump set M, construct the pump model combination set C based on the maximum number of different models selected by the user (the maximum number of different models allowed in the pump set).

[0184] 7. Iterate through each pump model combination in C. Assume that a certain pump model combination contains two pump models, A and B. The calculation process is illustrated in the example below (the same applies to more pump model combinations):

[0185] 1) Determine all possible pump combinations: For each type combination, start with 1 pump and gradually increase the number. For example, after determining 'a' type A pumps, find the minimum number of type B pumps that can satisfy the range of y values ​​in the sample set S, forming a pump combination to be used; subsequently, gradually increase the number of type A pumps and determine the number of type B pumps according to the same logic, until multiple type A pumps can meet the requirements and no more type B pumps are needed, then stop.

[0186] 2) Calculate the expected energy consumption of a pump combination with z pumps.

[0187] 8. As an option, when selecting pump combinations and determining the number of pumps of each model, a larger pump set can be added. The flow rate and head of the added pump should be the largest among the determined pumps to meet the standby requirements.

[0188] 9. As an option, when selecting pump combinations and determining the number of pumps of each model, the design flow rate and design head determined by local design specifications or standards can be used as the basis for selection. That is, the operating conditions designed according to specifications or standards are taken as a sample in S, and assigned a probability of one in ten thousand. This allows them to participate in the above selection process, ensuring that they meet the requirements of local design specifications.

[0189] 10. For each pump group, calculate its expected energy consumption cost within a specified time range. Subtract the expected energy consumption cost after the modification of each pump group from the historical actual operating energy consumption cost to obtain the expected savings cost within the specified time range. Without considering the purchase and installation costs of each pump group, use the expected savings cost within the specified time range as the sorting criterion to provide a recommended pump group modification plan.

[0190] 11. Given the availability of pump unit equipment purchase and installation costs, the investment return rate is calculated by subtracting the expected energy consumption cost of each pump unit after modification from the historical actual operating energy consumption cost. The investment payback period is then used as the ranking criterion to provide recommended pump unit modification schemes.

[0191] This application is particularly applicable to the field of water supply and drainage.

[0192] In practice, some domestic water companies measure the flow rate and inlet / outlet pressure of pump sets and then design them based on the maximum flow rate conditions from historical data. This approach is closer to actual conditions than selecting pumps according to national standards, but it doesn't consider the daily operating conditions. In other words, the selected pump sets may meet requirements under extreme conditions, but they cannot effectively improve operating efficiency for the majority of the time when the flow rate is not at its maximum. In water supply and drainage pump stations, to adapt to fluctuating operating conditions, a combination of large and small pumps is often used. This configuration is quite complex and cannot be covered by existing technologies. During the operation of water supply and drainage pumps, operating conditions fluctuate over time, and the probability of each condition occurring varies; existing technologies have not taken this into account.

[0193] The beneficial effects of the pump set selection method in this application are:

[0194] 1. The actual operating history boundary data of the pump house to be modified is used as the basis for pump set design, which departs from the traditional single-condition design and makes the selected pump set closer to the actual operating conditions.

[0195] 2. This scheme selects suitable pump sets and then conducts simulation operation. By simulating the operation of each pump set under the actual data distribution, it obtains energy consumption analysis results that are as close as possible to the actual operation of the pump sets, which serve as the basis for decision-making.

[0196] 3. The energy consumption values ​​obtained through simulation in this technical solution take into account the actual operating conditions under the combination of multiple pumps in parallel and multiple models;

[0197] 4. Using probability distributions or gridded discrete probability distributions for processing can reduce the amount of computation compared to directly calculating the data based on the original time series samples;

[0198] 5. Using the optimal frequency combination and its corresponding operating power that meet the operating conditions as the basis for calculating the future operation of the pump set can reflect the best operating effect of the pump set;

[0199] 6. By calculating the expected return on investment after replacing the pump set through long-term simulation, it is easier to make update decisions in combination with the source of funds;

[0200] 7. This solution is based on the two-dimensional probability distribution of historical operating conditions. It determines the expected energy consumption after commissioning through operating condition simulation calculations and selects pumps accordingly. By ensuring that the design operating conditions and other extreme operating conditions can be covered by the new pump set, the availability of the designed pump set is ensured.

[0201] This embodiment also provides a storage medium storing a computer program, which is executed by a processor to perform the pump selection method described in any of the above embodiments.

[0202] Finally, it should be noted that although the above embodiments have been described in the text and drawings of this application, this should not limit the scope of patent protection of this application. Any technical solutions that are based on the essential concept of this application and utilize the content described in the text and drawings of this application, resulting in equivalent structural or procedural substitutions or modifications, as well as the direct or indirect application of the technical solutions of the above embodiments to other related technical fields, are all included within the scope of patent protection of this application.

Claims

1. A pump set selection method based on time-delay simulation under actual operating conditions, characterized in that, Includes the following steps: S1: Obtain a sample set of historical data for the pump station. : In the formula, This represents the head of the pump unit at time t. This represents the flow rate of the pump unit at time t; S2: Based on the sample set Obtain the distribution model of head X and flow rate Y, and determine the value range of head X and flow rate Y; S3: Establish a database of candidate pump sets, including each candidate pump and its mapping relationship with flow rate, head, and speed: In the formula, The operating flow rate of the water pump with model number i; The operating head of the water pump with model number i is represented by its name. The rotational speed of the water pump with model number i; S4: Based on the distribution model of head X and flow rate Y constructed in step S2, determine the range of values ​​for head X. The mapping relationship between the head and speed of each candidate pump was selected from the database of candidate pump sets. Zhongyangcheng The domain includes The water pumps, and then construct a set of alternative water pumps M; S5: Construct a set of alternative water pump model combinations C based on the alternative water pump set M. The set of alternative water pump model combinations C includes combinations of different water pump models required by the user. S6: Based on the sample set Traffic in The range of values ​​is used to obtain the required number of each pump model in the set of candidate pump model combinations C, thus obtaining a feasible combination of pump model numbers. S7: Calculate the expected cost savings for each possible combination of pump models; S8: Output the number of feasible pump models that meet the requirements based on the expected cost savings.

2. The selection method according to claim 1, characterized in that, In step S7, the expected cost savings are obtained by subtracting the estimated energy consumption during the design period from the historical actual operating energy consumption of the pump house.

3. The selection method according to claim 2, characterized in that, In step S2, the distribution model includes the joint probability density function. ,in , The range of values ​​is ; In step S3, the candidate pump group database includes the mapping relationship between the operating power, speed, and flow rate of each candidate pump. ; Step S7 includes the following steps: In response to satisfy any operating point Determine if there are feasible speed values ​​for each pump. This ensures that the total flow rate provided by the combination of pump models satisfies the mass conservation equation constraint requirements: In the formula, This represents the i-th pump in the pump set being processed at the specified head. With rotational speed The output flow rate is below. Indicates the total number of water pumps; If so, the cost minimization function is obtained according to the following formula: In the formula, Represents the unit price of electricity. Representing the sampling frequency, in the process of solving the above-mentioned cost minimization function, the feasible speed values ​​of each pump should meet the requirements of the mass conservation equation; Based on the joint probability density function and the cost minimization function, the arbitrary value after replacing the water pump is obtained. Expected energy costs for the time period: The estimated energy cost during the design period is obtained based on the expected energy cost after replacing the water pump: 。 4. The selection method according to claim 2, characterized in that, In step S2, the two-dimensional probability distribution model includes a discrete distribution law. ; In the formula, the range of values ​​for x and y is: , The domain of the distribution of the two-dimensional discrete variable; In step S3, the candidate pump group database includes the mapping relationship between the operating power, speed, and flow rate of each candidate pump. ; Step S7 includes the following steps: For any operating point within the domain of the discrete distribution law of a two-dimensional discrete variable distribution. Determine if there are feasible speed values ​​for each pump. This ensures that the total flow rate provided by the combination of pump models satisfies the mass conservation equation constraint requirements: In the formula, This represents the i-th pump in the pump set being processed at the specified head. With rotational speed The output flow rate is below. Indicates the total number of water pumps; If so, the cost minimization function is obtained according to the following formula: In the formula, Represents the unit price of electricity. Representing the sampling frequency, in the process of solving the above-mentioned cost minimization function, the feasible speed values ​​of each pump should meet the requirements of the mass conservation equation; Based on the discrete distribution law and minimizing the cost function, the arbitrary value after replacing the water pump is obtained. Expected energy costs for the time period: The estimated energy cost within the design period t is obtained based on the expected energy cost after replacing the water pump: 。 5. The selection method according to claim 2, characterized in that, In step S3, the candidate pump group database includes the mapping relationship between the operating power, speed, and flow rate of each candidate pump. ; Step S7 includes the following steps: Based on sample set The sample set is processed as an equally weighted discrete model. any working point in Determine if there are feasible speed values ​​for each pump. This ensures that the total flow rate provided by the combination of pump models satisfies the mass conservation equation constraint requirements: In the formula, This represents the i-th pump in the pump set being processed at the specified head. With rotational speed The output flow rate is below. Indicates the total number of water pumps; If so, the cost minimization function is obtained according to the following formula: In the formula, Represents the unit price of electricity. Representing the sampling frequency, in the process of solving the above-mentioned cost minimization function, the feasible speed values ​​of each pump should meet the requirements of the mass conservation equation; Based on the sample set And minimizing the cost function to obtain the design period Expected energy costs within: ； In the formula, For sample set The length.

6. The selection method according to any one of claims 2 to 5, characterized in that, It also includes the following steps: Determine the unit price of electricity Is it time-of-use pricing? If so, then introduce the time dimension when constructing the distributed model. and the electricity unit price Replace with time-of-use electricity price This is used to minimize the cost function and calculate the expected energy consumption cost.

7. The selection method according to claim 1, characterized in that, Step S6 includes the following steps: For each pump model combination in the candidate pump combination set C, determine all feasible combinations of the number of pumps; wherein, feasible combinations of the number of pumps are generated in the following manner: In the set of candidate pump model combinations C, pumps of preset initial models are added incrementally, starting with a single pump. After each addition, the model is determined based on the sample set. Traffic in Determine the minimum number of pumps required for other models within the given range, and repeat the above process until the initial set of pumps can meet the sample set requirements. Traffic in The requirement is met until no other type of water pump is needed.

8. The selection method according to claim 1, characterized in that, In step S1, the sample set of historical data of the pump station It can be obtained through the following steps: The historical outflow, outlet pressure, and inlet pressure of the pump station are obtained for measurement. The sample set is obtained after processing the data based on outflow, outlet pressure, and inlet pressure. .

9. The selection method according to claim 1, characterized in that, Step S8 includes the following steps: Sort and output all feasible combinations of pump models based on the expected cost savings; or: Obtain the purchase price of each pump in all feasible combinations of pump models. Calculate the payback period for the investment based on the pump purchase price and the expected cost savings. Sort all feasible combinations of pump models according to the payback period and output the results.

10. A storage medium storing a computer program, characterized in that, The computer program, when executed by the processor, performs the pump selection method according to any one of claims 1 to 9.

Images