A method and device for detecting electrolyte of flow battery

Abstract

The present specification relates to the field of liquid flow battery energy storage technology, and in particular to a liquid flow battery electrolyte detection method and device. Among them, the liquid flow battery electrolyte detection method includes: controlling the sampling mechanism to extract the electrolyte in the electrolyte storage tank into the detection tank through the first delivery pipeline; detecting the density of the electrolyte in the detection tank; controlling the sampling mechanism to allow the electrolyte in the detection tank to flow back to the electrolyte storage tank via the first delivery pipeline; calculating the viscosity of the electrolyte according to the time when the electrolyte flows back to the electrolyte storage tank; determining the state of the electrolyte according to the density and viscosity of the electrolyte. The embodiments of this specification can directly perform rapid in-situ testing on the electrolyte, reduce safety hazards in the electrolyte detection process and reduce the waste of electrolyte in the detection process, thereby improving the overall safety, economy and timeliness. In addition, the density and viscosity of the electrolyte can be comprehensively determined to determine the state of the electrolyte, and then take corresponding measures.

Description

Technical Field

[0001] The embodiments of this specification relate to the technical field of liquid flow battery energy storage, and specifically to a method and device for detecting electrolyte in a liquid flow battery. Background Art

[0002] With the vigorous development of the new energy industry, the number of new energy storage and independent energy storage power stations has also increased rapidly. As a rapidly developing technology route in new energy storage, flow batteries have been applied in engineering. Flow batteries are composed of battery stacks, electrolytes, electrolyte storage tanks and pumps, management control units and auxiliary components (such as thermal management and safety systems). Among them, the electrolyte is the energy storage unit of the flow battery. During the use of the flow battery, the physical and chemical state of the electrolyte will have a great impact on the performance of the flow battery energy storage equipment.

[0003] The current mainstream electrolyte detection mode is abnormal detection. Specifically, it is to shut down the equipment when a problem occurs and take electrolyte samples through the valve at the battery stack. After the sampling is completed, the electrolyte status is analyzed in the laboratory.

[0004] However, the abnormal detection method has complicated operation process, great difficulty in operation, long time consumption, waste of electricity, waste of electrolyte, and great safety hazards, which cannot meet the normal monitoring of electrolyte status. Therefore, how to overcome the problems of complicated operation process, great difficulty in operation, long time consumption, waste of electricity, waste of electrolyte, and great safety hazards in the existing abnormal detection methods, and provide a flow battery electrolyte detection method that takes into account safety, economy and timeliness, so as to improve the operating status of energy storage equipment and reduce the complexity of equipment operation and maintenance is a key problem to be solved urgently. Summary of the invention

[0005] The purpose of the embodiments of this specification is to provide a liquid flow battery electrolyte detection method and device to overcome the problems of the existing abnormal detection methods, such as complicated operation process, difficult operation, long time consumption, waste of electricity, waste of electrolyte, and great safety hazards, and to provide a liquid flow battery electrolyte detection method that takes into account safety, economy and timeliness, thereby improving the operating status of energy storage equipment and reducing the complexity of equipment operation and maintenance.

[0006] On the one hand, the embodiments of this specification propose a liquid flow battery electrolyte detection method, which includes: controlling a sampling mechanism to extract electrolyte from an electrolyte storage tank into a detection tank through a first delivery pipeline; detecting the density of the electrolyte in the detection tank; controlling the sampling mechanism to allow the electrolyte in the detection tank to flow back to the electrolyte storage tank via the first delivery pipeline; calculating the viscosity of the electrolyte based on the time it takes for the electrolyte to flow back to the electrolyte storage tank; and determining the state of the electrolyte based on the density and viscosity of the electrolyte.

[0007] On the other hand, a liquid flow battery electrolyte detection device comprises: a first control module, used to control a sampling mechanism to extract electrolyte from an electrolyte storage tank into a detection tank through a first delivery pipeline; a detection module, used to detect the density of the electrolyte in the detection tank; a second control module, used to control the sampling mechanism to allow the electrolyte in the detection tank to flow back to the electrolyte storage tank via the first delivery pipeline; a calculation module, used to calculate the viscosity of the electrolyte based on the time it takes for the electrolyte to flow back to the electrolyte storage tank; and a determination module, used to determine the state of the electrolyte based on the density and viscosity of the electrolyte.

[0008] On the other hand, a detection device is provided, which is arranged on the electrolyte storage tank of the liquid flow battery; the detection device includes a first delivery pipeline, a detection tank, a sampling mechanism and a controller; one end of the first delivery pipeline is connected to the detection tank, and the other end extends into the electrolyte storage tank; the controller is used to execute the above-mentioned liquid flow battery electrolyte detection method.

[0009] It can be seen from the technical solutions provided in the above embodiments of this specification that the flow battery electrolyte detection method provided in the embodiments of this specification can control the sampling mechanism to extract the electrolyte in the electrolyte storage tank into the detection tank through the first delivery pipeline; detect the density of the electrolyte in the detection tank; control the sampling mechanism so that the electrolyte in the detection tank flows back to the electrolyte storage tank via the first delivery pipeline; calculate the viscosity of the electrolyte according to the time when the electrolyte flows back to the electrolyte storage tank; determine the state of the electrolyte according to the density and viscosity of the electrolyte. Compared with the existing methods, there is no need to shut down the equipment and sample the electrolyte through the valve at the battery stack, and the electrolyte can be directly tested quickly in situ, which reduces the safety hazards in the electrolyte detection process and reduces the waste of electrolyte in the detection process, and improves the overall safety, economy and timeliness. In addition, the density and viscosity of the electrolyte can be combined to more comprehensively determine the state of the electrolyte, and then take corresponding measures according to the state of the electrolyte. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the drawings required for use in the embodiments or the prior art description are briefly introduced below.

[0011] Figure 1 is a structural diagram of a detection device provided in an embodiment of this specification;

[0012] Figure 2 is a flow chart of a method for detecting electrolyte in a flow battery provided in an embodiment of this specification;

[0013] Figure 3It is a schematic diagram of the structural composition of a liquid flow battery electrolyte detection device provided in an embodiment of this specification.

[0014] Reference numerals in the above drawings:

[0015] 1. Electrolyte storage tank; 2. Positive / negative electrolyte; 3. Second delivery pipeline; 4. Flange; 5. Detection chamber; 6. Balance chamber; 7. First delivery pipeline; 8. Density detection ball; 9. Suction rod; 10. Transmission gear; 11. Pressure relief pipeline. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0017] Figure 1 A structural diagram of a detection device provided in an embodiment of this specification.

[0018] In some embodiments, the liquid flow battery includes an electrolyte storage tank; a detection device is provided on the electrolyte storage tank, and the detection device includes a first delivery pipeline, a detection tank and a sampling mechanism; one end of the first delivery pipeline is connected to the detection tank, and the other end extends into the interior of the electrolyte storage tank.

[0019] By providing a detection device on the electrolyte storage tank of the flow battery, the electrolyte can be directly and quickly tested in situ, reducing the safety hazards in the electrolyte detection process.

[0020] Reference Figure 1As shown, the flow battery includes an electrolyte storage tank 1. A detection device is provided on the electrolyte storage tank 1, and the detection device includes a first delivery pipeline 7, a detection tank and a sampling mechanism. One end of the first delivery pipeline 7 is connected to the detection tank, and the other end extends into the electrolyte storage tank 1. The first delivery pipeline 7 can be made of corrosion-resistant material and can be used to extract positive / negative electrolyte 2 from the electrolyte storage tank 1 to the detection tank. The electrolyte storage tank 1 is used to store the positive / negative electrolyte 2 of the flow battery, and the liquid level of the positive / negative electrolyte 2 usually floats in the height range of 80%-90%. The positive / negative electrolyte 2 is the main raw material for charging and discharging the flow battery. The detection tank is built-in with a partition plate, and the partition plate separates the detection tank into a detection chamber 5 and a balance chamber 6. The detection chamber 5 can be made of a transparent corrosion-resistant material, which can be used to detect the color and viscosity of the electrolyte, so as to quickly evaluate key state parameters such as the electrolyte concentration. The balance chamber 6 can be used to balance the internal air pressure of the detection chamber 5 and the external air pressure of the detection chamber 5 during the process of extracting the positive / negative electrolyte 2 into the detection chamber 5. The sampling mechanism includes a driving mechanism and a pipette rod 9. The driving mechanism includes a transmission gear 10. The transmission gear 10 can be an electric gear, which can be used to control the pipette rod 9 gear to pull the partition plate in the detection tank upward to extract the positive / negative electrolyte 2 into the detection chamber 5 when the detection switch is turned on. One end of the pipette rod 9 is connected to the transmission gear 10, and the other end is connected to the partition plate in the detection tank. The pipette rod 9 can be used to pull the partition plate in the detection tank upward to extract the positive / negative electrolyte 2 into the detection chamber 5 when the detection switch is turned on.

[0021] The detection device also includes a second delivery pipeline 3, a flange port 4, a density detection ball 8 and a pressure relief pipeline 11. The second delivery pipeline 3 can be used to transport the positive / negative electrolyte 2 of the liquid flow battery from the electrolyte storage tank 1 to the liquid flow battery stack for charging and discharging. The flange port 4 can be used for extracting or filling the positive / negative electrolyte 2 during daily inspection and maintenance. A density detection ball 8 is built into the detection chamber 5. The density detection ball 8 is made of corrosion-resistant material, and its density is within the density variation range of the positive / negative electrolyte 2. It can be used to evaluate the density of the positive / negative electrolyte 2 at the position scale in the detection chamber 5. The pressure relief pipeline 11 is a hollow structure, passing through the balance chamber 6 and communicating with the detection chamber 5. The pressure relief pipeline 11 can be used to release the air pressure in the detection chamber 5, so that the positive / negative electrolyte 2 flows back to the electrolyte storage tank 1 through the first delivery pipeline 7 under the action of gravity.

[0022] Corresponds to Figure 1 The detection device in this specification also provides a method for detecting electrolyte of a flow battery. Figure 2 A flow chart of a method for detecting electrolyte in a flow battery provided in an embodiment of this specification.

[0023] In specific implementation, the flow battery electrolyte detection method includes the following steps:

[0024] S201: Control the sampling mechanism to extract the electrolyte in the electrolyte storage tank into the detection tank through the first delivery pipeline.

[0025] In some embodiments, the sampling mechanism includes a driving mechanism and a pipette rod; the detection tank has a built-in partition plate; the partition plate divides the detection tank into a detection chamber and a balance chamber; one end of the pipette rod is connected to the driving mechanism, and the other end is connected to the partition plate; the sampling mechanism is controlled to extract electrolyte from the electrolyte storage tank into the detection tank through the first delivery pipeline, including: controlling the driving mechanism to drive the pipette rod to pull the partition plate, so that the electrolyte in the electrolyte storage tank enters the detection tank through the first delivery pipeline.

[0026] By pulling the suction rod to extract the electrolyte in the electrolyte storage tank into the detection chamber of the detection tank, a foundation is laid for rapid in-situ testing of the electrolyte, which helps to reduce safety hazards in the electrolyte detection process and reduce the waste of electrolyte.

[0027] See also Figure 2 As shown, the sampling mechanism includes a driving mechanism and a liquid suction rod 9. The driving mechanism includes a transmission gear 10. The detection tank is built with a partition plate, which divides the detection tank into a detection chamber 5 and a balance chamber 6. The detection chamber 5 can be made of a transparent corrosion-resistant material, and can be used to detect the color of the electrolyte, the viscosity of the electrolyte, and thus quickly evaluate key state parameters such as the electrolyte concentration. The balance chamber 6 can be used to balance the internal air pressure of the detection chamber 5 and the external air pressure of the detection chamber 5 during the process of extracting the positive / negative electrolyte 2 to the detection chamber 5. The transmission gear 10 can be an electric gear, which can be used to control the liquid suction rod 9 gear to pull the partition plate in the detection tank upward to extract the positive / negative electrolyte 2 to the detection chamber 5 when the detection switch is turned on. One end of the liquid suction rod 9 is connected to the transmission gear 10, and the other end is connected to the partition plate in the detection tank. The liquid suction rod 9 can be used to pull the partition plate in the detection tank upward to extract the positive / negative electrolyte 2 to the detection chamber 5 when the detection switch is turned on. When the pressure relief pipeline 11 is sealed, the detection switch can be turned on to control the transmission gear 10 to drive the liquid suction rod 9 to pull the partition plate in the detection tank, thereby extracting the positive / negative electrolyte 2 stored in the electrolyte storage tank 1. The extracted positive / negative electrolyte 2 can be transported to the detection chamber 5 via the first delivery pipeline 7.

[0028] S202: Detecting the density of the electrolyte in the detection tank.

[0029] In some embodiments, the detection tank is engraved with density scale lines; detecting the density of the electrolyte in the detection tank includes: determining the density of the electrolyte according to the position of a density detection ball in the detection tank and the density scale lines of the detection tank.

[0030] The density of the electrolyte is determined by the position of the density detection ball in the detection tank and the density scale line of the detection tank, which lays a data foundation for determining the state of the electrolyte.

[0031] The detection chamber 5 is engraved with density scale lines, which can be used to determine the density of the electrolyte. Specifically, each scale line on the detection chamber 5 corresponds to a specific density value, and the density of the positive / negative electrolyte 2 can be determined according to the density scale line corresponding to the density detection ball 8. A density detection ball 8 is built into the detection chamber 5. The density detection ball 8 is made of corrosion-resistant material, and its density is within the density variation range of the positive / negative electrolyte 2. It can be generally used to evaluate the density of the positive / negative electrolyte 2 at the position scale in the detection chamber 5. An appropriate amount of positive / negative electrolyte 2 can be extracted to ensure that the positive / negative electrolyte 2 can completely cover the density detection ball 8. The extracted positive / negative electrolyte 2 can be allowed to stabilize in the detection chamber 5 for a period of time to ensure that the density detection ball 8 can accurately reflect the density of the positive / negative electrolyte 2. When the density of the positive / negative electrolyte 2 changes, the position of the density detection ball 8 in the detection chamber 5 will also change accordingly. This is because the design of the density detection ball 8 causes it to be subjected to different buoyancy in liquids of different densities, thereby causing its position to change. The density of the positive / negative electrolyte 2 can be determined based on the density scale line corresponding to the density detection ball 8. For example, a pre-trained scale line image recognition model can be used to identify the density scale line corresponding to the density detection ball 8, thereby determining the density of the positive / negative electrolyte 2. Specifically, a scale line recognition model can be pre-trained using deep image processing models such as GAN, ResNet, Diffusion, and GNN. The pre-trained scale line image recognition model can accurately identify the density scale line corresponding to the density detection ball 8, thereby determining the density of the positive / negative electrolyte 2. For another example, the density detection ball 8 can be matched with the density scale line through visual comparison by the operator, thereby determining the density of the positive / negative electrolyte 2.

[0032] S203: Control the sampling mechanism to allow the electrolyte in the detection tank to flow back to the electrolyte storage tank via the first delivery pipeline.

[0033] In some embodiments, the sampling mechanism also includes a pressure relief pipeline; the pressure relief pipeline is connected to the detection chamber of the detection tank; the sampling mechanism is controlled so that the electrolyte in the detection tank flows back to the electrolyte storage tank via the first delivery pipeline, including: opening the pressure relief pipeline to release the air pressure in the detection chamber; when the air pressure in the detection chamber and the air pressure outside the detection chamber are balanced, the electrolyte in the detection chamber flows back to the electrolyte storage tank via the first delivery pipeline under the action of gravity.

[0034] By balancing the air pressure inside and outside the detection room to cause the electrolyte to flow back to the electrolyte storage tank through the first delivery pipeline under the action of gravity, waste of electrolyte resources is avoided and a foundation is laid for obtaining the viscosity of the electrolyte based on the quality of the electrolyte and the flow time of the electrolyte.

[0035] The sampling mechanism also includes a pressure relief line 11. The pressure relief line 11 is a hollow structure, passes through the balance chamber 6, and is connected to the detection chamber 5. The pressure relief line 11 can be used to release the air pressure in the detection chamber 5, so that the positive / negative electrolyte 2 flows back to the electrolyte storage tank 1 through the first delivery line 7 under the action of gravity. The pressure relief line 11 can be opened, and the air pressure inside the detection chamber 5 and the air pressure outside the detection chamber 5 will reach a balance. The positive / negative electrolyte 2 flows back to the electrolyte storage tank 1 through the first delivery line 7 under the action of gravity, which can reduce the waste of electrolyte caused by detection.

[0036] S204: Calculate the viscosity of the electrolyte according to the time it takes for the electrolyte to flow back to the electrolyte storage tank.

[0037] In some embodiments, the viscosity of the electrolyte is calculated based on the time it takes for the electrolyte to flow back to the electrolyte storage tank, including: obtaining the mass of the electrolyte in the detection tank; and calculating the viscosity of the electrolyte using a preset viscosity model based on the mass of the electrolyte and the time it takes for the electrolyte to flow back to the electrolyte storage tank via the first delivery pipeline.

[0038] By using the preset viscosity model to calculate the viscosity of the electrolyte, a data foundation is laid for determining the state of the electrolyte.

[0039] The flow time of the electrolyte in the suction line at different distances under gravity under different temperatures, pressures, masses and viscosities can be obtained in advance. A viscosity model of temperature, pressure, mass, distance, time and electrolyte viscosity can be established. For example, a viscosity model can be established using machine learning models such as K-Means, KNN, SVM, XGBoost, etc. Specifically, temperature, pressure, mass, distance and time can be used as input parameters of the viscosity model, and the viscosity model predicts the viscosity of the output electrolyte. The difference between the viscosity of the predicted electrolyte and the viscosity of the real electrolyte can be minimized until the viscosity model converges. The viscosity model can be used to predict the viscosity of the positive / negative electrolyte 2 according to the mass of the positive / negative electrolyte 2 in the detection chamber and the time when the positive / negative electrolyte 2 flows back to the electrolyte storage tank 1 under gravity. The mass sensor can be used to obtain the mass of the positive / negative electrolyte 2 in the detection chamber 5, and the timing sensor can be used to obtain the time for the positive / negative electrolyte 2 to flow back to the electrolyte storage tank 1 via the first delivery pipeline 7, and the length, ambient temperature, and ambient pressure of the first delivery pipeline 7 can be obtained. The mass of the positive / negative electrolyte 2 in the detection chamber 5, the time for the positive / negative electrolyte 2 to flow back to the electrolyte storage tank 1 via the first delivery pipeline 7, the length of the first delivery pipeline 7, the ambient temperature, and the ambient pressure can be input as input parameters into the pre-trained viscosity model, and the pre-trained viscosity model can output the viscosity of the positive / negative electrolyte 2.

[0040] S205: Determine the state of the electrolyte according to the density and viscosity of the electrolyte.

[0041] In some embodiments, an image corresponding to the electrolyte in the detection tank may be acquired; and based on the image corresponding to the electrolyte, a preset concentration model may be used to determine the concentration of the electrolyte.

[0042] The concentration of the electrolyte is determined by using a preset concentration model, which lays a data foundation for determining the state of the electrolyte.

[0043] The electrolyte concentration may refer to the total concentration of solutes (which may be salts, acids, bases, etc.) in the electrolyte, which includes the concentration contribution of all ions in the electrolyte. The concentration of the positive / negative electrolyte 2 may be the concentration of V (vanadium, or other chemical substances with V ions) ions in the positive / negative electrolyte 2. High concentrations of single V ions in flow batteries are prone to form precipitation, which may cause irreversible damage to the battery and reduce the active material. Therefore, when the color of the positive / negative electrolyte 2 of the flow battery approaches the color of a single valence electrolyte, charging and discharging should be stopped in time to ensure that the state of the positive / negative electrolyte 2 is stable.

[0044] An image sensor can be used to obtain an image of the positive / negative electrolyte 2 in the detection chamber 5. The historical images of the positive / negative electrolyte 2 during the historical operation and the corresponding concentration values ​​can be obtained. The normal historical images and abnormal historical images of the positive / negative electrolyte 2 can be preprocessed, including denoising, contrast enhancement, color correction, etc., to improve the quality of the image and the accuracy of the analysis. Deep image processing models such as GAN, ResNet, Diffusion, GNN, etc. can be used to extract features related to the electrolyte concentration from the preprocessed historical images, such as color, brightness, texture, etc., and then output the concentration of the electrolyte. For example, GAN can be used as a concentration model, and GAN can extract features related to the electrolyte concentration, such as color, brightness, texture, and output the concentration of the electrolyte. Specifically, the historical images of the positive / negative electrolyte 2 can be input into GAN, and GAN can predict the output concentration of the positive / negative electrolyte 2. Minimize the difference between the predicted concentration and the true concentration until GAN ​​converges. The image sensor can be used to obtain a real-time image of the positive / negative electrolyte 2 in the detection chamber 5, and the real-time image of the positive / negative electrolyte 2 is input into the pre-trained GAN, and the GAN can predict and output the concentration of the positive / negative electrolyte 2. Preferably, the image sensor and the concentration model can be regularly maintained and updated to ensure their long-term effectiveness and accuracy.

[0045] In some embodiments, based on the concentration, density and viscosity of the electrolyte, a preset electrolyte state detection model can be used to determine the state of the electrolyte; based on the state of the electrolyte, an electrolyte detection report can be generated; based on the electrolyte detection report, the electrolyte can be adjusted.

[0046] According to the concentration, density and viscosity of the electrolyte, a preset electrolyte state detection model can be used to more comprehensively and reasonably determine the state of the electrolyte, and then adjust the electrolyte according to the state of the electrolyte, which helps to prevent and improve abnormal conditions in a timely manner.

[0047] The electrolyte state detection model can be a machine learning model such as K-Means, KNN, SVM, XGBoost, or a rule / parameter model manually set based on the experience and knowledge of experts. According to the real-time concentration data, real-time density data and real-time viscosity data of the positive / negative electrolyte 2, the electrolyte state detection model can be used to more comprehensively and accurately evaluate the state of the positive / negative electrolyte 2. For example, the electrolyte state detection model can be K-Means. Specifically, the historical concentration data, historical density data, historical viscosity data and corresponding historical state data of the positive / negative electrolyte 2 can be obtained, and the historical concentration data, historical density data and historical viscosity data of the positive / negative electrolyte 2 can be spliced, fused or extracted to obtain the historical parameters of the positive / negative electrolyte 2. K-Means clustering can be performed on the historical parameters of the positive / negative electrolyte 2, and after the cluster center no longer changes, each cluster center is mapped to different historical state types. In the real-time detection stage, the real-time concentration data, real-time density data and real-time viscosity data of the positive / negative electrolyte 2 can be obtained. Similarly, after splicing, fusion or extraction, the real-time parameters of the positive / negative electrolyte 2 are obtained, the distance from the real-time parameters of the positive / negative electrolyte 2 to the cluster center is calculated, the nearest cluster center is determined, and the state of the positive / negative electrolyte 2 is determined according to the state type corresponding to the cluster center.

[0048] After comprehensively determining the state of the positive / negative electrolyte 2 according to the real-time concentration data, real-time density data and real-time viscosity data of the positive / negative electrolyte 2, a corresponding electrolyte detection report can be generated according to the real-time concentration data, real-time density data and real-time viscosity data of the positive / negative electrolyte 2. For example, the state of the positive / negative electrolyte 2 and the real-time concentration data, real-time density data and real-time viscosity data of the positive / negative electrolyte 2 can be input into a pre-trained large language model (such as BERT, GPT, etc.), and the pre-trained large language model can generate a detailed electrolyte detection report, including abnormal data, possible causes, impact on the system or equipment, and recommended solutions, such as replacing the electrolyte, adjusting the composition ratio of the electrolyte, changing the storage conditions, etc.

[0049] In some embodiments, when the electrolyte state is abnormal, the real-time SOC state of the electrolyte can be determined based on a preset SOC state model; if the real-time SOC state of the electrolyte is abnormal, the charging and discharging operation of the flow battery can be stopped.

[0050] For the concentration of positive / negative electrolyte 2, if the color of the positive electrolyte does not reach the standard pentavalent vanadium color when the SOC (battery state of charge) approaches 0, the electrolyte test report can report that the state of the positive / negative electrolyte 2 of the flow battery is abnormal, and the positive / negative electrolyte 2 needs to be further extracted to the laboratory for ion concentration detection and calibration. Deep image processing models such as GAN, ResNet, Diffusion, and GNN can be used to extract features related to the SOC state of the electrolyte from the reference images of the positive and negative electrolytes in different SOC states, and then output the SOC state of the electrolyte. For example, Diffusion can be used as an SOC state model, Diffusion can extract features related to the SOC state of the electrolyte and output the SOC state of the electrolyte. Specifically, multiple normal historical images with a SOC state of 0%-100% for the positive / negative electrolyte 2 can be input into Diffusion, and Diffusion can predict and output the SOC state of the positive / negative electrolyte 2. Minimize the difference between the predicted SOC state and the actual SOC state until the Diffusion converges. The image sensor can be used to obtain the real-time image of the positive / negative electrolyte 2 in the detection chamber 5, and the real-time image of the positive / negative electrolyte 2 is input into the pre-trained Diffusion. Diffusion can predict and output the SOC state of the positive / negative electrolyte 2. Preferably, the SOC state model can be regularly maintained and updated to ensure its long-term effectiveness and accuracy. After determining the SOC state of the positive / negative electrolyte 2 through the SOC state model, the reference image of the corresponding SOC state of the positive / negative electrolyte 2 under normal conditions and the real-time image of the positive / negative electrolyte 2 can be respectively given in the electrolyte detection report. If the SOC state of the positive / negative electrolyte 2 is abnormal, the electrolyte detection report can indicate to stop charging and discharging, and extract the positive and negative electrolytes 2 to the laboratory to analyze the cause of the failure.

[0051] In some embodiments, when the electrolyte state is abnormal, the electrolyte density deviation can be calculated; if the electrolyte density deviation reaches a preset density deviation threshold, the charge and discharge operation of the flow battery can be stopped.

[0052] As for the density of the positive / negative electrolyte 2, when the state of the positive / negative electrolyte 2 is abnormal, the electrolyte density deviation between the real-time density of the positive / negative electrolyte 2 and the preset standard density can be calculated. When the electrolyte density deviation reaches the preset density deviation threshold (for example, the density deviation threshold can be ±5%), the electrolyte detection report can indicate to stop charging and discharging, and extract the electrolyte to the laboratory for electrolyte state calibration, so as to ensure the safe and stable operation of the liquid flow battery.

[0053] In some embodiments, when the electrolyte state is abnormal, the electrolyte viscosity deviation may be calculated; if the electrolyte viscosity deviation reaches a preset viscosity deviation threshold, the vanadium ion concentration and the acid concentration in the electrolyte may be adjusted.

[0054] As for the viscosity of the positive / negative electrolyte 2, when the state of the positive / negative electrolyte 2 is abnormal, the electrolyte viscosity deviation between the real-time viscosity of the positive / negative electrolyte 2 and the preset standard viscosity can be calculated. When the electrolyte viscosity deviation reaches the preset viscosity deviation threshold (for example, the density deviation threshold can be ±10%), the electrolyte test report can be judged as abnormally low vanadium ion concentration and acid concentration, and it is recommended to extract the electrolyte to the laboratory for electrolyte state calibration. If it is found that the viscosity of the electrolyte has not changed significantly at a higher operating temperature, the electrolyte test report can recommend further testing whether the vanadium ion or acid concentration has increased. If it is finally determined that the vanadium ion concentration is too high, in order to maintain the stable operation of the system, a stabilizer needs to be added to the electrolyte to prevent the precipitation of vanadium ions and the reduction of active substances.

[0055] When any deep learning / machine learning model among the above scale line recognition model, concentration model, viscosity model, electrical state detection model and SOC state model is trained or optimized, the learning rate update process is as follows:

[0056] During the training process, gradient descent is used to update the deep learning model parameters according to the gradient descent algorithm of the Newton-Leibniz formula. The calculation formula is:

[0057] ;

[0058] Where ωj represents the jth parameter of the deep learning / machine learning model, ωj' is the corresponding updated parameter; λ represents the learning rate of the deep learning / machine learning model, which is used to determine the convergence rate of the deep learning / machine learning model; It represents the partial derivative of the loss function F(ωj) with respect to ωj when the deviation between the predicted result and the actual result of the deep learning / machine learning model is known. The deviation between the predicted result and the actual result can be calculated by the loss function; the loss function is usually defined based on the sum of squared errors between the predicted result and the actual result, or the absolute value of the error, logarithmic loss, etc. The deep learning / machine learning model adjusts the values ​​of various parameters in the model by the deviation between the predicted result and the actual result, so that the deviation becomes smaller and smaller.

[0059] In some embodiments, the learning rate can be set to a fixed value, or strategies such as learning rate decay, adaptive learning rate, and polynomial learning rate can be used. The idea of ​​learning rate decay is to gradually reduce the learning rate as training progresses to improve the stability and generalization of model training. Adaptive learning rate is a type of strategy that can automatically adjust the learning rate. It can dynamically adjust the learning rate according to the gradient information of the parameters, thereby improving the training speed and performance of the model. The idea of ​​polynomial decay is to decay the learning rate through a polynomial function, thereby gradually reducing the learning rate during training. It can help the model converge better in the later stages of training and improve the generalization ability of the model.

[0060] As can be seen from the above, based on the flow battery electrolyte detection method provided in the embodiment of this specification, the sampling mechanism can be controlled to extract the electrolyte in the electrolyte storage tank into the detection tank through the first delivery pipeline; the density of the electrolyte is detected in the detection tank; the sampling mechanism is controlled so that the electrolyte in the detection tank flows back to the electrolyte storage tank via the first delivery pipeline; the viscosity of the electrolyte is calculated according to the time when the electrolyte flows back to the electrolyte storage tank; the state of the electrolyte is determined according to the density and viscosity of the electrolyte. Compared with the existing method, there is no need to shut down the equipment and sample the electrolyte through the valve at the battery stack, and the electrolyte can be directly tested quickly in situ, which reduces the safety hazards in the electrolyte detection process and reduces the waste of electrolyte in the detection process, thereby improving the overall safety, economy and timeliness. In addition, the density and viscosity of the electrolyte can be combined to more comprehensively determine the state of the electrolyte, and then corresponding measures can be taken according to the state of the electrolyte.

[0061] Based on the above-mentioned liquid flow battery electrolyte detection method, this specification also proposes an embodiment of a liquid flow battery electrolyte detection device. Figure 3 As shown, the flow battery electrolyte detection device 300 may specifically include the following modules:

[0062] The first control module 301 may be used to control the sampling mechanism to extract the electrolyte in the electrolyte storage tank into the detection tank through the first delivery pipeline;

[0063] A detection module 302, which can be used to detect the density of the electrolyte in the detection tank;

[0064] The second control module 303 may be used to control the sampling mechanism so that the electrolyte in the detection tank flows back to the electrolyte storage tank via the first delivery pipeline;

[0065] The calculation module 304 may be used to calculate the viscosity of the electrolyte according to the time it takes for the electrolyte to flow back to the electrolyte storage tank;

[0066] The determination module 305 may be used to determine the state of the electrolyte according to the density and viscosity of the electrolyte.

[0067] In some embodiments, the first control module 301 can be specifically used to control the driving mechanism to drive the liquid suction rod to pull the partition plate so that the electrolyte in the electrolyte storage tank enters the detection tank through the first delivery pipeline.

[0068] In some embodiments, the detection module 302 may be specifically used to determine the density of the electrolyte according to the position of the density detection ball in the detection tank and the density scale line of the detection tank.

[0069] In some embodiments, the second control module 303 can be specifically used to open the pressure relief pipeline to release the air pressure in the detection chamber; when the air pressure in the detection chamber and the air pressure outside the detection chamber are balanced, the electrolyte in the detection chamber flows back to the electrolyte storage tank through the first delivery pipeline under the action of gravity.

[0070] In some embodiments, the calculation module 304 can be specifically used to obtain the mass of the electrolyte in the detection tank; and calculate the viscosity of the electrolyte using a preset viscosity model according to the mass of the electrolyte and the time it takes for the electrolyte to flow back to the electrolyte storage tank via the first delivery pipeline.

[0071] In some embodiments, the determination module 305 may be specifically used to obtain an image corresponding to the electrolyte in the detection tank; and determine the concentration of the electrolyte using a preset concentration model according to the image corresponding to the electrolyte.

[0072] In some embodiments, the above-mentioned determination module 305 can also be specifically used to determine the state of the electrolyte according to the concentration, density and viscosity of the electrolyte using a preset electrolyte state detection model; generate an electrolyte detection report according to the state of the electrolyte; and adjust the electrolyte according to the electrolyte detection report.

[0073] As can be seen from the above, based on the flow battery electrolyte detection device provided in the embodiment of this specification, the sampling mechanism can be controlled to extract the electrolyte in the electrolyte storage tank into the detection tank through the first delivery pipeline; the density of the electrolyte is detected in the detection tank; the sampling mechanism is controlled so that the electrolyte in the detection tank flows back to the electrolyte storage tank via the first delivery pipeline; the viscosity of the electrolyte is calculated according to the time when the electrolyte flows back to the electrolyte storage tank; the state of the electrolyte is determined according to the density and viscosity of the electrolyte. Compared with the existing method, there is no need to shut down the equipment and sample the electrolyte through the valve at the battery stack, and the electrolyte can be directly tested quickly in situ, which reduces the safety hazards in the electrolyte detection process and reduces the waste of electrolyte in the detection process, thereby improving the overall safety, economy and timeliness. In addition, the density and viscosity of the electrolyte can be combined to more comprehensively determine the state of the electrolyte, and then corresponding measures can be taken according to the state of the electrolyte.

[0074] It should be noted that the units, devices or modules described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described separately by functions divided into various modules. Of course, when implementing this specification, the functions of each module can be implemented in the same or more software and / or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0075] In order to complete the above instructions more accurately, refer to Figure 1 As shown, an embodiment of this specification provides a specific detection device, which is arranged on the electrolyte storage tank of the liquid flow battery; the detection device includes a first delivery pipeline, a detection tank, a sampling mechanism and a controller; one end of the first delivery pipeline is connected to the detection tank, and the other end extends into the electrolyte storage tank; the controller is used to execute the above-mentioned liquid flow battery electrolyte detection method.

[0076] The controller can be specifically used to control the sampling mechanism to extract the electrolyte in the electrolyte storage tank into the detection tank through the first delivery pipeline; detect the density of the electrolyte in the detection tank; control the sampling mechanism to make the electrolyte in the detection tank flow back to the electrolyte storage tank through the first delivery pipeline; calculate the viscosity of the electrolyte based on the time it takes for the electrolyte to flow back to the electrolyte storage tank; and determine the state of the electrolyte based on the density and viscosity of the electrolyte.

[0077] It should be understood by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0079] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0081] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting electrolyte of a flow battery, characterized in that: The liquid flow battery comprises an electrolyte storage tank; a detection device is arranged on the electrolyte storage tank, and the detection device comprises a first delivery pipeline, a detection tank and a sampling mechanism; one end of the first delivery pipeline is connected to the detection tank, and the other end extends into the electrolyte storage tank; the sampling mechanism comprises a liquid suction rod and a pressure relief pipeline; the liquid flow battery electrolyte detection method comprises: Controlling the liquid suction rod to pull the partition plate built into the detection tank, so as to extract the electrolyte in the electrolyte storage tank into the detection tank through the first delivery pipeline; Detecting the density of the electrolyte in the detection tank; Controlling the pressure relief pipeline to release the air pressure in the detection tank, so that the electrolyte in the detection tank flows back to the electrolyte storage tank through the first delivery pipeline under the action of gravity; Calculate the viscosity of the electrolyte based on the time it takes for the electrolyte to flow back to the electrolyte storage tank; Determine the state of the electrolyte using a preset electrolyte state detection model according to the concentration, density and viscosity of the electrolyte; generating an electrolyte detection report according to the state of the electrolyte; The electrolyte is adjusted according to the electrolyte detection report.

2. The method according to claim 1, characterized in that: The sampling mechanism also includes a driving mechanism; the partition plate divides the detection tank into a detection chamber and a balance chamber; one end of the liquid pipetting rod is connected to the driving mechanism, and the other end is connected to the partition plate; The control of the liquid suction rod to pull the partition plate built into the detection tank to extract the electrolyte in the electrolyte storage tank into the detection tank through the first delivery pipeline includes: The control driving mechanism drives the liquid suction rod to pull the partition plate, so that the electrolyte in the electrolyte storage tank enters the detection tank through the first delivery pipeline.

3. The method according to claim 1, characterized in that: The detection tank is engraved with density scale lines; The step of detecting the density of the electrolyte in the detection tank comprises: The density of the electrolyte is determined according to the position of the density detection ball in the detection tank and the density scale line of the detection tank.

4. The method according to claim 1, characterized in that: The pressure relief pipeline is connected to the detection chamber of the detection tank.

5. The method according to claim 4, characterized in that: The control pressure relief pipeline releases the air pressure in the detection tank so that the electrolyte in the detection tank flows back to the electrolyte storage tank through the first delivery pipeline under the action of gravity, including: The pressure relief pipeline is opened to release the air pressure in the detection chamber; when the air pressure in the detection chamber and the air pressure outside the detection chamber are balanced, the electrolyte in the detection chamber flows back to the electrolyte storage tank through the first delivery pipeline under the action of gravity.

6. The method according to claim 1, characterized in that: The calculating the viscosity of the electrolyte according to the time for the electrolyte to flow back to the electrolyte storage tank comprises: Obtain the mass of the electrolyte in the test tank; The viscosity of the electrolyte is calculated using a preset viscosity model according to the mass of the electrolyte and the time for the electrolyte to flow back to the electrolyte storage tank via the first delivery pipeline.

7. The method according to claim 1, characterized in that: The method further comprises: Acquire an image corresponding to the electrolyte in the detection tank; According to the image corresponding to the electrolyte, the concentration of the electrolyte is determined using a preset concentration model.

8. A flow battery electrolyte detection device, characterized in that: The device comprises: A first control module is used to control the liquid suction rod to pull the partition plate built into the detection tank, so as to extract the electrolyte in the electrolyte storage tank into the detection tank through the first delivery pipeline; A detection module, used for detecting the density of the electrolyte in the detection tank; The second control module is used to control the pressure relief pipeline to release the air pressure in the detection tank, so that the electrolyte in the detection tank flows back to the electrolyte storage tank through the first delivery pipeline under the action of gravity; A calculation module, used for calculating the viscosity of the electrolyte according to the time for the electrolyte to flow back to the electrolyte storage tank; A determination module is used to determine the state of the electrolyte according to the concentration, density and viscosity of the electrolyte using a preset electrolyte state detection model; generate an electrolyte detection report according to the state of the electrolyte; and adjust the electrolyte according to the electrolyte detection report.

9. A detection device, characterized in that: The detection device is arranged on the electrolyte storage tank of the liquid flow battery; the detection device includes a first delivery pipeline, a detection tank, a sampling mechanism and a controller; one end of the first delivery pipeline is connected to the detection tank, and the other end extends into the electrolyte storage tank; the sampling mechanism includes a liquid suction rod and a pressure relief pipeline; the controller is used to execute the method described in any one of claims 1-7.

Images