Water replenishment prediction method, device and storage medium for circulating water system

Abstract

The present invention provides a method, device, and storage medium for predicting water replenishment in a circulating water system. The method comprises: obtaining historical operating data of the circulating water system under various operating conditions, including water concentration ratio, production water consumption, and retained water volume; training a neural network based on the historical water concentration ratio, production water consumption, and retained water volume under each operating condition to determine the changing trends of the water concentration ratio, production water consumption, and retained water volume under each operating condition; establishing a water replenishment prediction model corresponding to each operating condition based on the changing trends of the water concentration ratio, production water consumption, and retained water volume; using the water replenishment prediction model to predict the changing trend of the retained water volume under the current operating condition, and adjusting the replenishment and drainage volume of the circulating water system based on the prediction results. The present invention improves the accuracy and reliability of adjusting the replenishment and drainage volume of the circulating water system.

Description

Technical Field

[0001] The present invention relates to the technical field of circulating water systems, and in particular to a method, device and storage medium for predicting water replenishment of a circulating water system. Background Art

[0002] Circulating water systems are widely used in industrial sectors such as steel, chemicals, automobiles, and textiles. The steel industry's water use process includes water intake, industrial water production, circulating cooling water, and wastewater treatment and reuse. As the most crucial component of the steel industry's water supply, the circulating water system's primary function is to indirectly cool key equipment within steel plants, providing cooling media for production processes such as blast furnaces, steelmaking, and rolling mills, ensuring safe equipment operation and product quality. Within a circulating water system, water losses occur during production, purification, cooling, and transportation. Therefore, the system must introduce new water to compensate for these losses. This replenishment, known as the system's drainage volume, directly impacts its operating efficiency, energy consumption, water quality, and environmental protection. Numerous factors influence drainage volume, including water losses due to evaporation during the circulation process, water losses due to seepage during pipeline transportation, water consumption in the sludge system, and the amount of wastewater discharged to maintain a certain concentration factor. In the related art, the prediction of replenishment and drainage volume usually relies on manual experience or a simple calculation model related to water loss to predict the replenishment and drainage volume, so as to replenish the circulating water system according to the predicted replenishment and drainage volume.

[0003] However, relying on manual experience or simple calculation models related to water loss, there is a lack of comprehensive analysis of changes in multiple influencing factors in water replenishment prediction, making it difficult to accurately reflect the actual operating status and changing trends of the circulating water system. This can easily lead to problems such as excessive or insufficient replenishment and drainage, resulting in high or low concentration ratios, thereby affecting the stability and reliability of the circulating water system operation, and increasing operating costs and environmental risks. Summary of the Invention

[0004] In view of the above-mentioned shortcomings of the prior art, the present invention provides a water replenishment prediction method, device and storage medium for a circulating water system to solve at least one of the above-mentioned technical problems.

[0005] In a first aspect, the present invention provides a method for predicting water replenishment of a circulating water system, comprising: obtaining historical working data of the circulating water system under various operating conditions, the historical data including historical water concentration multiples, historical production water consumption and historical retained water volume; training a neural network according to the historical water concentration multiples, the historical production water consumption and the historical retained water volume under each of the operating conditions, determining the changing trend of the water concentration multiples, the changing trend of the production water consumption and the changing trend of the retained water volume under each of the operating conditions, wherein the respective changing trends of the water concentration multiples and the production water consumption affect the changing trend of the retained water volume; establishing a water replenishment prediction model corresponding to the operating condition type according to the changing trend of the water concentration multiples, the changing trend of the production water consumption and the changing trend of the retained water volume; using the water replenishment prediction model to predict the changing trend of the retained water volume under the current operating condition, and adjusting the replenishment and drainage volume of the circulating water system based on the prediction result.

[0006] In one embodiment of the present invention, determining the changing trend of the water concentration multiple, the changing trend of the production water consumption and the changing trend of the retained water volume under each of the operating condition types includes: obtaining the starting product quantity and the ending product quantity produced under each of the operating conditions; determining the product production trend corresponding to each of the operating conditions based on the starting product quantity and the ending product quantity under each of the operating conditions in each of the operating condition types; marking the historical water concentration multiple, the historical production water consumption and the historical retained water volume in each of the operating conditions according to the product production trend to form a first training sample set; training the first neural network based on the first training sample set of each of the operating condition types to obtain a trend determination model corresponding to each of the operating condition types, the trend determination model including a first trend model, a second trend model and a third trend model, wherein the first trend model is used to output the changing trend of the water concentration multiple, the second trend model is used to output the changing trend of the production water consumption, and the third trend model is used to output the changing trend of the retained water volume.

[0007] In one embodiment of the present invention, the water replenishment prediction model corresponding to the operating condition type is established based on the changing trend of the water concentration multiple, the changing trend of the production water consumption and the changing trend of the retained water volume, including: marking the changing trends of the water concentration multiple, the production water consumption and the retained water volume under each of the operating condition types to form a second training sample set; training a second neural network based on the second training sample set of each of the operating condition types to obtain the water replenishment prediction model corresponding to each of the operating condition types; wherein, when training the second neural network, the changing trend of the water concentration multiple and the changing trend of the production water consumption are used as inputs of the second neural network, and the changing trend of the retained water volume is used as output of the second neural network.

[0008] In one embodiment of the present invention, the water replenishment prediction model is used to predict the changing trend of the retained water volume under the current operating conditions, and the replenishment and drainage volume of the circulating water system is adjusted based on the prediction results, including obtaining the current changing trend of the water concentration multiple, the current changing trend of the production water consumption and the current retained water volume of the circulating water system under the target operating condition type; inputting the current retained water volume, the current changing trend of the water concentration multiple and the current changing trend of the production water consumption into the water replenishment prediction model corresponding to the target operating condition type to determine the current changing trend of the retained water volume; and adjusting the replenishment and drainage volume of the circulating water system according to the current changing trend of the retained water volume.

[0009] In one embodiment of the present invention, before obtaining the current change trend of the water concentration multiple of the circulating water system and the current change trend of the production water consumption, it also includes: obtaining production performance, production plan and the current water concentration multiple and current production water consumption of the circulating water system, the production performance includes the current product type and current product quantity actually produced, and the production plan includes the planned product type and planned product quantity planned to be produced; screening from each trend determination model according to the current product type and the planned product type to determine the target trend determination model, the target trend determination model includes a target first trend model and a target second trend model; determining the current product production trend according to the previous product quantity and the planned product quantity; inputting the current product production trend and the current water concentration multiple, the current product production trend and the current production water consumption into the target first trend model and the target second trend model respectively to obtain the current change trend of the water concentration multiple and the current change trend of the production water consumption.

[0010] In one embodiment of the present invention, the target trend determination model is determined by screening from each of the trend determination models according to the current product type and the planned product type, including: obtaining production performance and production plan, the production performance including the actual product type and current product quantity actually produced, and the production plan including the planned product type and planned product quantity planned to be produced; determining the current operating condition type and the planned operating condition type according to the actual product type and the planned product type respectively; if the current operating condition type and the planned operating condition type are consistent, the current operating condition type is used as the target operating condition type; if the current operating condition type and the planned operating condition type are inconsistent, the planned operating condition type is used as the target operating condition type; and the trend determination model corresponding to the target operating condition type is determined as the target trend determination model.

[0011] In one embodiment of the present invention, after obtaining the current change trend of the water concentration multiple and the current change trend of the production water consumption, it also includes: comparing the water concentration multiple within the current change trend of the water concentration multiple and a preset sewage discharge threshold; if there is a production moment when the water concentration multiple is higher than the preset sewage discharge threshold in the current change trend of the water concentration multiple, then the circulating water system is caused to discharge sewage at the production moment.

[0012] In one embodiment of the present invention, the historical working data of the circulating water system under each operating condition type is obtained, and the historical data include historical water concentration multiples, historical production water consumption and historical retained water volume, including: obtaining the historical water concentration multiples, historical production water consumption and historical retained water volume of the circulating water system under each of the operating conditions, and the type of product produced under each of the operating conditions; classifying the operating conditions according to the product type corresponding to each of the operating conditions, and determining the operating condition type of each of the operating conditions; clustering the historical water concentration multiples, historical production water consumption and historical retained water volume under the same operating condition type, and determining the historical water concentration multiples, historical production water consumption and historical retained water volume under each operating condition type.

[0013] In a second aspect, the present invention also provides a water replenishment prediction device for a circulating water system, characterized in that it includes: an acquisition module for acquiring historical working data of the circulating water system under various operating conditions, the historical data including water concentration multiple, production water consumption and retained water volume; a trend determination module for training a neural network according to the historical water concentration multiple, the historical production water consumption and the historical retained water volume under each of the operating conditions, and determining the changing trend of the water concentration multiple, the changing trend of the production water consumption and the changing trend of the retained water volume under each of the operating conditions, wherein the respective changing trends of the water concentration multiple and the production water consumption affect the changing trend of the retained water volume; a model establishment module for establishing a water replenishment prediction model corresponding to the operating condition type according to the changing trend of the water concentration multiple, the changing trend of the production water consumption and the changing trend of the retained water volume; a water replenishment prediction module for using the water replenishment prediction model to predict the changing trend of the retained water volume under the current operating condition, and adjust the replenishment and drainage volume of the circulating water system based on the prediction result.

[0014] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer executes the water replenishment prediction method for the circulating water system as described in the above embodiment.

[0015] Beneficial effects of the present invention: The present invention proposes a water replenishment prediction method, device and storage medium for a circulating water system, which obtains historical working data of the circulating water system under various operating conditions, wherein the historical data include historical water concentration multiples, historical production water consumption and historical retained water volume; a neural network is trained according to the historical water concentration multiples, the historical production water consumption and the historical retained water volume under each of the operating conditions, and the changing trend of the water concentration multiples, the changing trend of the production water consumption and the changing trend of the retained water volume under each of the operating conditions are determined, wherein the water concentration multiples and the production water consumption affect the changing trend of the retained water volume; a water replenishment prediction model corresponding to the operating condition type is established according to the changing trend of the water concentration multiples, the changing trend of the production water consumption and the changing trend of the retained water volume; the water replenishment prediction model is used to predict the changing trend of the retained water volume under the current operating condition, and the replenishment and drainage volume of the circulating water system is adjusted based on the prediction result. On the one hand, the replenishment prediction of the circulating water system takes into account the water quality and the amount of water lost in various aspects during water circulation, that is, the historical water concentration multiples and historical production water consumption are involved in the construction of the replenishment prediction model, so as to predict the changing trend of the retained water volume according to the replenishment prediction model, and adjust the replenishment and drainage volume in time, thereby improving the accuracy and reliability of the replenishment and drainage volume adjustment; on the other hand, the changing trends of various parameters of the circulating water system under different working conditions are different. If the replenishment prediction is carried out separately for each type of working condition, it is not only universal, but also can make targeted adjustments to the replenishment and drainage volume of the circulating water system under each working condition, making the adjustment more accurate.

[0016] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and it is clear that a person skilled in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0018] Figure 1 is a flow chart of a method for predicting water replenishment in a circulating water system according to an exemplary embodiment of the present invention;

[0019] Figure 2 is a flow chart showing a method of determining a current trend of water concentration multiples and production water consumption according to an exemplary embodiment of the present invention;

[0020] Figure 34 is a block diagram of a water replenishment prediction device for a circulating water system according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0022] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0023] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0024] See also Figure 1 , is a flow chart of a method for predicting water replenishment in a circulating water system according to an exemplary embodiment of the present invention. Figure 1 As shown, in an exemplary embodiment, the method for predicting water replenishment of a circulating water system includes at least steps S110 to S140, which are described in detail as follows:

[0025] Step S110 , obtaining historical operating data of the circulating water system under various operating conditions, the historical data including historical water concentration multiples, historical production water consumption, and historical retained water volume.

[0026] In one embodiment of the present invention, the historical water concentration factor can reflect the water quality of the circulating water system and can be obtained by analyzing data such as online conductivity and offline water quality testing of the circulating water in the circulating water system. Online conductivity data can be read from relevant online instruments, while offline water quality testing data generally refers to data that requires manual entry, including production plans, water quality test reports, and other data. The historical retained water volume can be calculated based on the liquid levels of each water tank in the circulating water system. Historical production water consumption includes the sum of water lost in various ways during the historical operation of the circulating water system, including water lost due to evaporation during the circulation process, water lost due to pipe seepage, water consumed by the sludge system, and water consumed by backwashing of the filtration facilities.

[0027] Specifically, the historical working data of each operating condition type is determined in the following way: the historical water concentration multiple, historical production water consumption and historical retained water volume of the circulating water system under each operating condition, as well as the type of product produced under each operating condition, are obtained; the operating conditions are classified according to the product type corresponding to each operating condition, and the operating condition type of each operating condition is determined; the historical water concentration multiple, historical production water consumption and historical retained water volume under the same operating condition type are clustered separately, and the historical water concentration multiple, historical production water consumption and historical retained water volume under each operating condition type are determined.

[0028] In one embodiment of the present invention, due to the different types of products produced, the number of products produced in the same time period is different. For example, some types of products are produced intermittently, and they need to wait for one minute after every ten minutes of production before they can be produced again. Compared with the types of products that can be produced continuously, even if the number of products produced per minute of the two types of products is the same, the final number of products produced by the two types of products is different. Therefore, the impact of different product types on the historical water concentration multiple, historical production water consumption and historical retained water volume during the historical production process is also different. Therefore, it is necessary to divide each working condition according to the product type to facilitate separate analysis of the replenishment and drainage volume of the circulating water system under each working condition type.

[0029] In one embodiment of the present invention, the three parameters of historical water concentration multiple, historical production water consumption and historical retained water volume generated by the circulating water system in historical operation are all second-level data, and the amount of data is huge. In order to better analyze the changing trends of these three parameters, it is necessary to cluster the historical water concentration multiple, historical production water consumption and historical retained water volume separately, and divide the three parameters under the same working condition type together.

[0030] In one embodiment of the present invention, since the dimension, density and noise of the second-level data of industrial circulating water (historical water concentration multiples, historical production water consumption and historical retained water volume) are relatively high, clustering can be performed using the K-means algorithm (i.e., a clustering algorithm based on Euclidean distance), the DBSCAN algorithm (i.e., a density-based clustering algorithm), etc., and this embodiment does not limit this.

[0031] Through the above method, the relevant parameters of the circulating water system are divided according to the working condition type, so that the subsequent model construction can be targeted.

[0032] Step S120: Training a neural network based on the historical water concentration ratio, historical production water consumption, and historical retained water volume under each operating condition type to determine the changing trend of the water concentration ratio, the changing trend of the production water consumption, and the changing trend of the retained water volume under each operating condition type. The changing trends of the water concentration ratio and the production water consumption respectively affect the changing trend of the retained water volume.

[0033] Specifically, the change in historical retained water volume is due to a certain amount of water loss during the water circulation process, which causes a decrease in historical retained water volume. Furthermore, to maintain stable operation of the circulating water system, the system needs to be replenished. This replenished water volume is called the drainage volume, and the drainage volume is usually equal to the total water loss of the circulating water system as a whole, i.e., the change in retained water volume. The drainage volume is affected by the water concentration factor and production water consumption. Therefore, the changing trends of the water concentration factor and production water consumption affect the changing trends of the retained water volume.

[0034] In one embodiment of the present invention, the replenishment and drainage volume includes the historical production water consumption, which is the sum of water losses due to evaporation, water losses due to pipe seepage, water consumption in the sludge system, and water consumption due to backwashing of the filtration facilities, as well as the wastewater generated by the circulating water system due to poor water quality caused by excessive changes in the historical water concentration factor. Therefore, under various operating conditions, the replenishment and drainage volume = historical production water consumption + wastewater volume. The wastewater volume can be roughly calculated as: wastewater volume = water losses due to evaporation / (water concentration factor - 1).

[0035] Specifically, the starting number of products and the ending number of products produced under each operating condition are obtained; the product production trend corresponding to each operating condition is determined based on the starting number of products and the ending number of products under each operating condition in each operating condition type; the historical water concentration multiple, historical production water consumption and historical retained water volume in each operating condition are respectively marked according to the product production trend to form a first training sample set; based on the first training sample set of each operating condition type, the first neural network is trained respectively to obtain a trend determination model corresponding to each operating condition type, and the trend determination model includes a first trend model, a second trend model and a third trend model, wherein the first trend model is used to output the changing trend of the water concentration multiple, the second trend model is used to output the changing trend of the production water consumption, and the third trend model is used to output the changing trend of the retained water volume.

[0036] In one embodiment of the present invention, during the historical operation of the circulating water system, as the number of products produced continues to increase, the historical water concentration multiple and production water consumption will generally increase, and the historical retained water volume will generally decrease. That is to say, the trend of product production, that is, the changing trend of product quantity affects the corresponding changing trends of the historical water concentration multiple, historical production water consumption and historical retained water volume. Therefore, it is necessary to take the product production trend into consideration in the training of the first neural network, so as to construct a trend determination model, and a corresponding trend determination model is constructed for each operating condition type, thereby improving the accuracy and reliability of using the trend determination model to predict water concentration multiple and production water consumption.

[0037] Step S130 , establishing a water replenishment prediction model corresponding to the working condition type according to the changing trend of the water concentration multiple, the changing trend of the production water consumption and the changing trend of the retained water volume.

[0038] Specifically, the changing trends of the water concentration ratio, production water consumption and retained water volume under each operating condition type are marked to form a second training sample set; the second neural network is trained based on the second training sample set of each operating condition type to obtain a water replenishment prediction model corresponding to each operating condition type; wherein, when training the second neural network, the changing trends of the water concentration ratio and the changing trends of the production water consumption are used as the input of the second neural network, and the changing trend of the retained water volume is used as the output of the second neural network.

[0039] In one embodiment of the present invention, since the changing trend of the retained water volume is affected by the changing trend of the water concentration multiple and the changing trend of the production water consumption under the same operating conditions, the changing trend of the retained water volume, the changing trend of the water concentration multiple and the changing trend of the production water consumption corresponding to each operating condition are used as training samples, and the training samples under the same operating condition type are used as the second training sample set. Then, the second neural network is trained to establish a corresponding water replenishment prediction model for each operating condition type, so as to clarify the correlation between the two changing trends corresponding to the water concentration multiple and the production water consumption under each operating condition type and the changing trend of the retained water volume.

[0040] In one embodiment of the present invention, the types of the first neural network and the second neural network may be multilayer perceptron or long short-term memory network, etc., which is not limited in this embodiment.

[0041] In one embodiment of the present invention, optimization algorithms such as NEAT algorithm (i.e., genetic algorithm) and ES (Evolution Strategies) algorithm can be used to optimize each water replenishment prediction model and each trend determination model, and the fitness and generalization ability of the above models can be improved through operations such as mutation and recombination.

[0042] In the same way as above, the water replenishment prediction model is used to predict the changing trend of the retained water volume, that is, when predicting the replenishment and drainage volume, multiple factors (the changing trends of water concentration multiples and production water consumption) are comprehensively considered, thereby improving the accuracy of water replenishment prediction.

[0043] Step S140 , using the water replenishment prediction model to predict the change trend of the retained water volume under the current working conditions, and adjusting the replenishment and drainage volume of the circulating water system based on the prediction result.

[0044] Specifically, based on the predicted changing trend of the retained water volume, we can know the changing trend of the amount of water that is reduced in the retained water volume, that is, the changing trend of the total water loss during the future operation of the circulating water system, that is, the changing trend of the replenishment and drainage volume. Therefore, based on the predicted changing trend of the retained water volume, the replenishment and drainage volume can be adjusted.

[0045] See also Figure 2 , is a flow chart showing a current trend of determining the retained water volume according to an exemplary embodiment of the present invention. Figure 2 As shown, in an exemplary embodiment, determining the current change trends of the water concentration multiple and the production water consumption respectively includes at least steps S210 to S230, which are described in detail as follows:

[0046] Step S210, obtaining the current change trend of the water concentration ratio, the current change trend of the production water consumption, and the current retained water volume of the circulating water system under the target operating condition type;

[0047] In one embodiment of the present invention, the current retained water volume can be directly calculated based on the current liquid level of each water tank in the circulating water system. Starting from the current retained water volume, the future changes in the retained water volume, that is, the current change trend of the retained water volume, can be predicted.

[0048] Step S220: Input the current retained water volume, the current change trend of the water concentration ratio, and the current change trend of the production water consumption into the water replenishment prediction model corresponding to the target operating condition type to determine the current change trend of the retained water volume;

[0049] Specifically, the neural network model of the water replenishment prediction model is used to output the current change trend of the retained water volume to predict how the current retained water volume will decrease in the future. The current change trend of the retained water volume includes the values ​​of the retained water volume at various production moments in the future starting from the current retained water volume.

[0050] Step S230: adjusting the replenishment and drainage volume of the circulating water system according to the current change trend of the retained water volume.

[0051] In one embodiment of the present invention, because the circulating water system has a certain buffering capacity, its related operations of water replenishment and sewage discharge are not urgent. In actual production, if there is no need to adjust the replenishment and drainage volume in real time, a predicted water replenishment threshold can be set. If there is a production moment when the retained water volume is less than the preset water replenishment threshold in the current change trend of the retained water volume, the replenishment and drainage volume of the circulating water system is adjusted at the production moment when the retained water volume is less than the preset water replenishment threshold.

[0052] Through the above method, the replenishment and drainage volume can be adjusted in time according to the prediction results, thereby improving the reliability of the circulating water system.

[0053] Specifically, determining the current change trends corresponding to the water concentration ratio and the production water consumption includes: obtaining the production performance, production plan and current water concentration ratio of the circulating water system, and the current production water consumption, the production performance includes the current product type and the current product quantity actually produced, and the production plan includes the planned product type and the planned product quantity planned to be produced; screening from each trend determination model according to the current product type and the planned product type to determine the target trend determination model, the target trend determination model includes the target first trend model and the target second trend model; determining the current product production trend according to the previous product quantity and the planned product quantity; inputting the current product production trend and the current water concentration ratio, the current product production trend and the current production water consumption into the target first trend model and the target second trend model respectively to obtain the current change trend of the water concentration ratio and the current change trend of the production water consumption.

[0054] In one embodiment of the present invention, because each operating condition type corresponds to a trend determination model, it is necessary to determine the trend determination model corresponding to the operating condition type to which the actual operating condition belongs and use it as the target trend determination model. This makes the water replenishment prediction of the circulating water system in the present invention applicable to various production types and universal.

[0055] Specifically, after determining the current change trend of the water concentration multiple, it also includes: comparing the water concentration multiple within the current change trend of the water concentration multiple and the preset sewage discharge threshold; if there is a production moment in the current change trend of the water concentration multiple when the water concentration multiple is higher than the preset sewage discharge threshold, then the circulating water system is caused to discharge sewage at the production moment.

[0056] In one embodiment of the present invention, the water concentration ratio is an important comprehensive indicator for measuring water quality. If the water concentration ratio is too high, the water's tendency to scale increases, resulting in poor water quality, which in turn reduces the operating efficiency of the circulating water system and increases energy consumption. To control the water concentration ratio of circulating water within a reasonable range, the current trend of the water concentration ratio is observed to determine whether there are production moments where the water concentration ratio exceeds a preset sewage discharge threshold. If so, the circulating water system is caused to discharge sewage at these production moments, controlling the water concentration ratio to remain within a reasonable range and ensuring good water quality. In this embodiment, the preset sewage discharge threshold can be adjusted based on actual production conditions.

[0057] Through the above method, the operating efficiency of the circulating water system can be improved and the energy consumption can be reduced.

[0058] Specifically, the target trend determination model is determined in the following way:

[0059] Obtain production performance and production plan, where production performance includes the actual product type and current product quantity actually produced, and production plan includes the planned product type and planned product quantity planned to be produced; determine the current operating condition type and the planned operating condition type according to the actual product type and the planned product type respectively; if the current operating condition type is consistent with the planned operating condition type, use the current operating condition type as the target operating condition type; if the current operating condition type is inconsistent with the planned operating condition type, use the planned operating condition type as the target operating condition type; determine the trend determination model corresponding to the target operating condition type as the target trend determination model.

[0060] In one embodiment of the present invention, because the types of products currently being produced and the types of products planned for future production may change, that is, the operating condition type may change, it is necessary to select a corresponding trend determination model. Therefore, it is determined whether the current operating condition type and the planned operating condition type are consistent. If they are consistent, the target trend determination model is the trend determination model corresponding to the current operating condition type; if they are inconsistent, the target trend determination model is the trend determination model corresponding to the planned operating condition type. It should be understood that if the planned product types are adjusted, the target trend determination model needs to be reselected.

[0061] See also Figure 3 , which is a block diagram of a water replenishment prediction device for a circulating water system according to an exemplary embodiment of the present invention. The exemplary water replenishment prediction device for a circulating water system includes: an acquisition module 310 , a trend determination module 320 , a model building module 330 , and a water replenishment prediction module 340 .

[0062] An acquisition module 310 is configured to acquire historical operating data of the circulating water system under various operating conditions, wherein the historical data includes historical water concentration multiples, historical production water consumption, and historical retained water volume;

[0063] a trend determination module 320 for training a neural network based on the historical water concentration ratios, the historical production water consumption, and the historical retained water volume under each of the operating conditions, to determine a changing trend of the water concentration ratio, the production water consumption, and the retained water volume under each of the operating conditions, wherein the changing trends of the water concentration ratio and the production water consumption affect the changing trend of the retained water volume;

[0064] A model building module 330 is configured to build a water replenishment prediction model corresponding to the operating condition type according to the changing trend of the water concentration multiple, the changing trend of the production water consumption, and the changing trend of the retained water volume;

[0065] The water replenishment prediction module 340 is used to use the water replenishment prediction model to predict the change trend of the retained water volume under the current working conditions, and adjust the replenishment and drainage volume of the circulating water system based on the prediction result.

[0066] It should be noted that the water replenishment prediction device for the circulating water system provided in the above embodiment and the water replenishment prediction method for the circulating water system provided in the above embodiment are based on the same concept. The specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the water replenishment prediction device for the circulating water system provided in the above embodiment can, as needed, allocate the above functions to different functional modules, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0067] The improved water replenishment prediction device for the circulating water system of the present invention, on the one hand, takes into account the water quality and the amount of water lost in various aspects during water circulation, and even takes the historical water concentration multiples and historical production water consumption into consideration in the construction of the water replenishment prediction model, so as to predict the changing trend of the retained water volume according to the water replenishment prediction model, and adjust the replenishment and drainage volume in time, thereby improving the accuracy and reliability of the replenishment and drainage volume adjustment; on the other hand, the changing trends of various parameters of the circulating water system under different working conditions are different. If water replenishment prediction is performed separately for each working condition type, it is not only universal, but also can make targeted adjustments to the replenishment and drainage volume of the circulating water system under each working condition, making the adjustment more accurate.

[0068] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer executes the aforementioned method for predicting water replenishment in a circulating water system.

[0069] It should be noted that the computer-readable medium shown in the embodiments of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium may, for example, be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take a variety of forms, including, but not limited to, an electromagnetic signal, an optical signal, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0070] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0071] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, any equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical principles disclosed herein are intended to be covered by the claims of the present invention.

Claims

1. A method for predicting water replenishment in a circulating water system, characterized in that: include: Obtain historical operating data of the circulating water system under various operating conditions, including historical water concentration ratios, historical production water consumption, and historical retained water volume. The historical production water consumption includes the total amount of water lost by the circulating water system in various ways during its historical operation. The total amount of water includes the amount of water lost due to evaporation during the circulation process, the amount of water lost due to pipeline infiltration, the amount of water consumed by the sludge system, and the amount of water consumed by backwashing of the filtration facilities. Training a neural network based on the historical water concentration ratio, the historical production water consumption, and the historical retained water volume under each of the operating conditions, determining a change trend of the water concentration ratio, a change trend of the production water consumption, and a change trend of the retained water volume under each of the operating conditions, wherein the change trends of the water concentration ratio and the production water consumption respectively affect the change trend of the retained water volume; Establishing a water replenishment prediction model corresponding to the operating condition type according to the changing trend of the water concentration multiple, the changing trend of the production water consumption, and the changing trend of the retained water volume; Using the water replenishment prediction model to predict the change trend of the retained water volume under the current working conditions, and adjusting the replenishment and drainage volume of the circulating water system based on the prediction results; The water replenishment prediction model corresponding to the operating condition type is established based on the changing trend of the water concentration multiple, the changing trend of the production water consumption and the changing trend of the retained water volume, including: marking the changing trends of the water concentration multiple, the production water consumption and the retained water volume under each of the operating condition types to form a second training sample set; training a second neural network based on the second training sample set of each of the operating condition types to obtain the water replenishment prediction model corresponding to each of the operating condition types; wherein, when training the second neural network, the changing trend of the water concentration multiple and the changing trend of the production water consumption are used as inputs of the second neural network, and the changing trend of the retained water volume is used as output of the second neural network.

2. The method for predicting water replenishment in a circulating water system according to claim 1, wherein: Determining the changing trend of the water concentration multiple, the changing trend of the production water consumption, and the changing trend of the retained water volume under each of the operating conditions includes: Obtain the starting quantity and ending quantity of products produced under each of the working conditions; Determine the product production trend corresponding to each of the working conditions according to the starting product quantity and the ending product quantity under each of the working conditions in each of the working condition types; The historical water concentration multiples, the historical production water consumption, and the historical retained water volume in each of the working conditions are respectively labeled according to the product production trend to form a first training sample set; The first neural network is trained based on the first training sample set of each operating condition type to obtain a trend determination model corresponding to each operating condition type. The trend determination model includes a first trend model, a second trend model and a third trend model, wherein the first trend model is used to output the changing trend of the water concentration multiple, the second trend model is used to output the changing trend of the production water consumption, and the third trend model is used to output the changing trend of the retained water volume.

3. The method for predicting water replenishment in a circulating water system according to claim 1, wherein: The water replenishment prediction model is used to predict the change trend of the retained water volume under the current working conditions, and the replenishment and drainage volume of the circulating water system is adjusted based on the prediction result, including: Obtaining a current change trend of the water concentration multiple, a current change trend of the production water consumption, and a current retained water volume of the circulating water system under a target operating condition type; Inputting the current retained water volume, the current change trend of the water concentration multiple, and the current change trend of the production water consumption into the water replenishment prediction model corresponding to the target operating condition type to determine the current change trend of the retained water volume; The replenishment and drainage volume of the circulating water system is adjusted according to the current change trend of the retained water volume.

4. The method for predicting water replenishment in a circulating water system according to claim 3, wherein: Before obtaining the current change trend of the water concentration multiple and the current change trend of the production water consumption of the circulating water system, the method further includes: Obtaining actual production performance, a production plan, and the current water concentration multiple and current production water consumption of the circulating water system, wherein the actual production performance includes the current product type and current product quantity actually produced, and the production plan includes the planned product type and planned product quantity planned to be produced; Filtering from each of the trend determination models according to the current product type and the planned product type to determine a target trend determination model, the target trend determination model including a target first trend model and a target second trend model; Determine the current product production trend based on the previous product quantity and the planned product quantity; The current product production trend and the current water concentration multiple, the current product production trend and the current production water consumption are input into the target first trend model and the target second trend model respectively to obtain the current change trend of the water concentration multiple and the current change trend of the production water consumption.

5. The method for predicting water replenishment of a circulating water system according to claim 4, wherein: The step of screening the trend determination models according to the current product type and the planned product type to determine a target trend determination model includes: Acquire production performance and production plan, wherein the production performance includes the actual product type and current product quantity actually produced, and the production plan includes the planned product type and planned product quantity planned to be produced; Determine the current operating condition type and the planned operating condition type respectively according to the actual product type and the planned product type; If the current operating condition type is consistent with the planned operating condition type, the current operating condition type is used as the target operating condition type; If the current operating condition type is inconsistent with the planned operating condition type, the planned operating condition type is used as the target operating condition type; The trend determination model corresponding to the target operating condition type is determined as the target trend determination model.

6. The method for predicting water replenishment in a circulating water system according to claim 4, wherein: After obtaining the current change trend of the water concentration multiple and the current change trend of the production water consumption, the method further includes: comparing the water concentration multiple within a current variation trend of the water concentration multiple with a preset sewage discharge threshold; If there is a production moment when the water concentration multiple is higher than the preset sewage discharge threshold value in the current change trend of the water concentration multiple, the circulating water system is caused to discharge sewage at the production moment.

7. The method for predicting water replenishment in a circulating water system according to claim 1, wherein: The historical operating data of the circulating water system under various operating conditions is obtained, wherein the historical operating data includes historical water concentration multiples, historical production water consumption, and historical retained water volume, including: Obtaining the historical water concentration multiple, the historical production water consumption, and the historical retained water volume of the circulating water system under each of the operating conditions, as well as the type of product produced under each of the operating conditions; Classify the working conditions according to the product types corresponding to the working conditions, and determine the working condition type of each working condition; The historical water concentration multiples, the historical production water consumption and the historical retained water volume under the same operating condition type are clustered respectively to determine the historical water concentration multiples, the historical production water consumption and the historical retained water volume under each operating condition type.

8. A water replenishment prediction device for a circulating water system, characterized in that: include: an acquisition module for acquiring historical operating data of the circulating water system under various operating conditions, the historical operating data including historical water concentration multiples, historical production water consumption, and historical water retention capacity. The historical production water consumption includes the sum of water losses in various aspects of the circulating water system during its historical operation. The sum of water includes water lost due to evaporation during the circulation process, water lost due to pipeline infiltration, water consumed by the sludge system, and water consumed by backwashing of the filtration facility; a trend determination module, configured to train a neural network based on the historical water concentration ratio, the historical production water consumption, and the historical retained water volume under each of the operating conditions, and determine a changing trend of the water concentration ratio, a changing trend of the production water consumption, and a changing trend of the retained water volume under each of the operating conditions, wherein the changing trends of the water concentration ratio and the production water consumption respectively affect the changing trend of the retained water volume; A model building module, configured to build a water replenishment prediction model corresponding to the operating condition type according to a changing trend of the water concentration multiple, a changing trend of the production water consumption, and a changing trend of the retained water volume; a water replenishment prediction module, configured to use the water replenishment prediction model to predict a change trend of the retained water volume under the current working conditions, and adjust the replenishment and drainage volume of the circulating water system based on the prediction result; The model building module is specifically used to mark the respective changing trends of the water concentration ratio, the production water consumption and the retained water volume under each of the operating condition types to form a second training sample set; based on the second training sample set of each of the operating condition types, a second neural network is trained to obtain the water replenishment prediction model corresponding to each of the operating condition types; wherein, when training the second neural network, the changing trends of the water concentration ratio and the production water consumption are used as inputs of the second neural network, and the changing trends of the retained water volume are used as outputs of the second neural network.

9. A computer-readable storage medium, characterized in that A computer program is stored thereon, and the computer program is used to enable a computer to execute the water replenishment prediction method for a circulating water system according to any one of claims 1 to 7.

Images