A control method for microbial agent expansion and automatic dosing equipment

Abstract

The present invention relates to the technical field of microbial expansion equipment, and in particular to a control method for microbial agent expansion and automatic dosing equipment. The preset parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at several preset time nodes are obtained; the characteristic parameters in the data storage library are classified and processed; the actual parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at several preset time nodes are obtained according to the classification results; the characteristic parameters in the microbial agent expansion and automatic dosing equipment are analyzed according to the actual parameter values ​​and preset parameter values ​​of each characteristic parameter at several preset time nodes; if the working state of the microbial agent expansion and automatic dosing equipment is an abnormal state, the microbial agent expansion and automatic dosing equipment is regulated and processed, so as to realize the real-time regulation of the microbial agent expansion and automatic dosing equipment, and significantly improve the operation efficiency and stability of the equipment.

Description

Technical Field

[0001] The invention relates to the technical field of microbial culture expansion equipment, in particular to a control method for microbial agent culture expansion and automatic dosing equipment. Background Art

[0002] In modern industrial production and agricultural development, microbial agents are widely used in food fermentation, biopharmaceuticals, environmental protection, agricultural planting and other fields due to their unique biological activity and efficient functional characteristics. In recent years, microbial agent expansion and automatic dosing equipment has developed rapidly. This type of equipment integrates advanced automatic control systems, precise measuring instruments and intelligent decision-making algorithms, and can monitor and control various parameters in the expansion process in real time, automatically adjust the amount and speed of nutrient addition, effectively avoid the uncertainty of manual operation, and significantly improve the expansion efficiency and agent quality.

[0003] However, although the existing microbial inoculant expansion and automatic dosing equipment have achieved remarkable results in improving production efficiency, there are a series of technical and practical challenges in the development and application of microbial inoculant expansion and automatic dosing equipment: First, precise control of the microbial growth environment is a complex issue. The growth of microorganisms is affected by many factors, including temperature, pH value, oxygen content, nutrient concentration, etc., and the interaction between these factors is complex and difficult to accurately simulate and control. Secondly, the concentration of microbial inoculants needs to be precisely adjusted according to the expansion stage and target application, and the accuracy, stability, response speed and integration of the automatic dosing system with the overall control system are key issues that need to be addressed; the reliability and durability of the system are also important considerations, especially in the scenarios of long-term operation and large-scale application. In addition, in order to optimize the control strategy, a large amount of operating data needs to be collected and analyzed, including microbial growth parameters, environmental parameters, equipment performance, etc. The efficient processing, pattern recognition, anomaly detection and data-based decision support of these data require powerful computing power and advanced algorithm support. Summary of the invention

[0004] The invention overcomes the shortcomings of the prior art and provides a control method for microbial agent expansion and automatic dosing equipment.

[0005] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is:

[0006] The first aspect of the present invention discloses a control method for a microbial agent expansion and automatic dosing equipment, comprising the following steps:

[0007] Obtaining preset control index requirements for microbial agent expansion and automatic dosing equipment, and determining preset parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at a number of preset time nodes according to the preset control index requirements;

[0008] During the operation of the microbial agent expansion and automatic dosing equipment, the actual parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment are collected in sequence at a number of preset time nodes, and the actual parameter values ​​of the characteristic parameters collected are stored in a data storage library;

[0009] After the collection is completed, the characteristic parameters in the data storage are classified and processed, and the classification results are output; according to the classification results, the actual parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at several preset time nodes are obtained;

[0010] Analyze each characteristic parameter in the microbial agent expansion and automatic dosing equipment according to the actual parameter value and the preset parameter value of each characteristic parameter at several preset time nodes, and obtain the working status of the microbial agent expansion and automatic dosing equipment by analysis;

[0011] If the working state of the microbial agent expansion and automatic dosing equipment is normal, the microbial agent expansion and automatic dosing equipment will not be regulated; if the working state of the microbial agent expansion and automatic dosing equipment is abnormal, a recommended regulation plan is generated, and the microbial agent expansion and automatic dosing equipment is regulated.

[0012] More specifically, the characteristic parameters in the data repository are classified and processed, and the classification results are output, specifically:

[0013] Constructing a grid system, dividing the grid system into a plurality of sub-grid spaces, obtaining characteristic parameters in a data storage repository, and mapping the characteristic parameters in the data storage repository to each sub-grid space respectively;

[0014] Acquire text features of feature parameters in each sub-grid space, and calculate mutual information values ​​between feature parameters in each sub-grid space based on the text features of feature parameters in each sub-grid space;

[0015] The feature parameters whose mutual information values ​​are greater than a preset threshold are marked as strongly associated feature parameters, and the sub-grid spaces to which the feature parameters whose mutual information values ​​are greater than the preset threshold belong are merged, so as to aggregate all the feature parameters marked as strongly associated to obtain several aggregated spaces; wherein each aggregated space aggregates feature parameters with information sharing;

[0016] Calculate the mean of all characteristic parameters in each aggregation space, and determine the aggregation center of each aggregation space according to the calculated mean;

[0017] Calculate the Manhattan distance from all feature parameters in each aggregation space to the aggregation center, square the Manhattan distance from all feature parameters in each aggregation space to the aggregation center, and obtain the contribution value of each feature parameter to the discreteness of the aggregation space to which it belongs;

[0018] The contribution values ​​of all characteristic parameters in each aggregation space are added together to obtain the total dispersion of each aggregation space. The total dispersion of each aggregation space is divided by the total number of all characteristic parameters in the aggregation space to obtain the average dispersion of each aggregation space.

[0019] The average discreteness of each aggregation space is compared with the preset discreteness threshold; if the average discreteness of an aggregation space is greater than the preset discreteness threshold, the aggregation space is marked as a high-variance space; if the average discreteness of an aggregation space is not greater than the preset discreteness threshold, the aggregation space is marked as a low-variance space;

[0020] De-noising the aggregation space marked as a high-variance space to obtain a denoised aggregation space, and performing time series-based sorting on the characteristic parameters in the denoised aggregation space;

[0021] The aggregation space marked as low-variance space is not subjected to denoising, and the characteristic parameters in the aggregation space that is not subjected to denoising are sorted based on time series;

[0022] After processing, the classification results are output.

[0023] More specifically, the aggregation space marked as high-variance space is denoised to obtain the denoised aggregation space, which is:

[0024] Obtain all aggregate spaces marked as high-variance spaces, and define them as aggregate spaces to be denoised;

[0025] The DBSCAN algorithm is introduced, and the neighborhood radius and the minimum number of samples are preset; the aggregation space to be denoised is obtained, and the total number of feature parameters of each feature parameter in the aggregation space to be denoised within the preset domain radius is calculated;

[0026] Compare the total number of feature parameters of each feature parameter within the preset domain radius with the minimum number of samples;

[0027] If the total number of feature parameters of a certain feature parameter within the preset domain radius is greater than or equal to the minimum number of samples, the feature parameter is marked as a density-reachable feature parameter of the aggregation space to be denoised;

[0028] If the total number of feature parameters of a certain feature parameter within the preset domain radius is less than the minimum number of samples, the feature parameter is marked as a non-density-reachable feature parameter of the aggregation space to be denoised;

[0029] By analogy, the non-density-reachable characteristic parameters of each aggregation space to be denoised are detected based on the DBSCAN algorithm;

[0030] The non-density-reachable feature parameters in each aggregation space to be denoised are screened out to obtain the denoised aggregation space.

[0031] More specifically, the characteristic parameters in the microbial agent expansion and automatic dosing equipment are analyzed according to the actual parameter values ​​and preset parameter values ​​of each characteristic parameter at several preset time nodes, and the working status of the microbial agent expansion and automatic dosing equipment is obtained by analysis, specifically:

[0032] Constructing a plurality of two-dimensional coordinate systems, and constructing actual parameter value curve graphs and preset parameter value curve graphs of each characteristic parameter according to actual parameter values ​​and preset parameter values ​​of each characteristic parameter at a plurality of preset time nodes in the corresponding two-dimensional coordinate systems;

[0033] Calculating the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in each two-dimensional coordinate system; and comparing the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in each two-dimensional coordinate system with a preset overlap rate threshold;

[0034] If the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in a certain two-dimensional coordinate system is not greater than the preset overlap rate threshold, the corresponding characteristic parameter in the microbial inoculant expansion and automatic dosing equipment is calibrated as a drift characteristic parameter;

[0035] If the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in a certain two-dimensional coordinate system is greater than the preset overlap rate threshold, the corresponding characteristic parameters in the microbial inoculant expansion and automatic dosing equipment are calibrated as normal characteristic parameters;

[0036] Determine whether drift characteristic parameters appear in the microbial agent expansion and automatic dosing equipment; if drift characteristic parameters appear, mark the working status of the microbial agent expansion and automatic dosing equipment as abnormal; if no drift characteristic parameters appear, mark the working status of the microbial agent expansion and automatic dosing equipment as normal.

[0037] More specifically, if the working state of the microbial agent expansion and automatic dosing equipment is abnormal, a recommended control scheme is generated, and the microbial agent expansion and automatic dosing equipment is controlled, specifically:

[0038] Obtaining assembly drawing information of the microbial agent expansion and automatic dosing equipment, and constructing a three-dimensional model diagram of the equipment for the microbial agent expansion and automatic dosing equipment according to the assembly drawing information;

[0039] If the working state of the microbial agent expansion and automatic dosing equipment is abnormal, obtain the real-time parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment, integrate the real-time parameter values ​​of each characteristic parameter into the equipment three-dimensional model diagram using PROE software, and establish a real-time simulation model diagram of the microbial agent expansion and automatic dosing equipment;

[0040] If the working state of the microbial agent expansion and automatic dosing equipment is abnormal, the drift characteristic parameters in the microbial agent expansion and automatic dosing equipment are obtained at the same time;

[0041] Constructing search keywords based on the drift characteristic parameters in the microbial agent expansion and automatic dosing equipment, searching the shared database according to the search keywords, and retrieving several control schemes; and obtaining the control parameters of each control scheme;

[0042] PROE software is used to simulate and control the real-time simulation model diagram of microbial agent expansion and automatic dosing equipment based on the control parameters of each control scheme, and the simulation parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment after the simulation and control of each control scheme are obtained; and the control time required for the simulation and control of each control scheme is obtained.

[0043] The following steps are also included:

[0044] According to the control time required for the simulation control of each control scheme, the predicted working time node of the microbial agent expansion culture and automatic dosing equipment after the simulation control of each control scheme is determined;

[0045] Determine the standard parameter range value of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at the predicted working time node according to the preset control index requirements;

[0046] Determine whether the simulation parameter values ​​of each characteristic parameter in the microbial agent expansion culture and automatic dosing equipment after the simulation control of each control scheme are within the corresponding standard parameter range value;

[0047] Obtaining a control scheme in which all simulation parameter values ​​are within the corresponding standard parameter range values, and obtaining an energy consumption loss value of the control scheme in which all simulation parameter values ​​are within the corresponding standard parameter range values;

[0048] The control scheme with the lowest energy consumption loss value is taken as the recommended control scheme, and the microbial agent expansion culture and automatic dosing equipment are regulated according to the recommended control scheme.

[0049] More specifically, the characteristic parameters include the temperature, dissolved oxygen, pH, stirring speed, water addition amount and foam amount of the activation tank;

[0050] The characteristic parameters also include the stirring speed of the liquid storage tank and the discharge flow rate of the metering pump;

[0051] The characteristic parameters also include the amount of bacteria added to the dilution tank, the amount of tap water, the stirring speed, and the discharge flow rate of the high-pressure pump.

[0052] The second aspect of the present invention discloses a control system for microbial agent expansion and automatic dosing equipment, the control system includes a memory and a processor, the memory stores a control method program for microbial agent expansion and automatic dosing equipment, when the control method program for microbial agent expansion and automatic dosing equipment is executed by the processor, the steps of any one of the control methods for microbial agent expansion and automatic dosing equipment are implemented.

[0053] The third aspect of the present invention discloses a computer-readable storage medium, which includes a control method program for microbial inoculant expansion and automatic dosing equipment. When the control method program for microbial inoculant expansion and automatic dosing equipment is executed by a processor, the steps of any one of the control methods for microbial inoculant expansion and automatic dosing equipment are implemented.

[0054] The present invention solves the technical defects existing in the background technology, and has the following beneficial effects: obtaining preset parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at several preset time nodes; sequentially collecting the actual parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at several preset time nodes, and classifying the characteristic parameters in the data storage library; obtaining the actual parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at several preset time nodes according to the classification results; analyzing each characteristic parameter in the microbial agent expansion and automatic dosing equipment according to the actual parameter values ​​and preset parameter values ​​of each characteristic parameter at several preset time nodes; if the working state of the microbial agent expansion and automatic dosing equipment is an abnormal state, generating a recommended control plan, and controlling the microbial agent expansion and automatic dosing equipment, the entire control process realizes the refined management and real-time monitoring of the microbial agent expansion and automatic dosing equipment in an automated manner, and significantly improves the operation efficiency and stability of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0056] Figure 1 It is a flow chart of the overall method of the control method of the microbial agent expansion and automatic dosing equipment;

[0057] Figure 2 It is a partial method flow chart of the control method of the microbial agent expansion and automatic dosing equipment;

[0058] Figure 3 System block diagram of the control system for the microbial agent expansion and automatic dosing equipment;

[0059] Figure 4 This is the process flow chart for the expansion and automatic dosing equipment of microbial agents. DETAILED DESCRIPTION

[0060] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0061] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0062] like Figure 1 As shown, the first aspect of the present invention discloses a control method for microbial agent expansion and automatic dosing equipment, comprising the following steps:

[0063] S102: obtaining preset control index requirements of the microbial agent expansion and automatic dosing equipment, and determining preset parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at a number of preset time nodes according to the preset control index requirements;

[0064] S104: during the operation of the microbial agent expansion and automatic dosing equipment, the actual parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment are collected in sequence at a number of preset time nodes, and the collected actual parameter values ​​of the characteristic parameters are stored in a data storage library;

[0065] S106: After the collection is completed, the characteristic parameters in the data storage are classified and processed, and the classification results are output; according to the classification results, the actual parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at several preset time nodes are obtained;

[0066] S108: analyzing each characteristic parameter in the microbial agent expansion and automatic dosing equipment according to the actual parameter value and the preset parameter value of each characteristic parameter at a plurality of preset time nodes, and obtaining the working state of the microbial agent expansion and automatic dosing equipment through analysis;

[0067] S110: If the working state of the microbial agent expansion and automatic dosing equipment is normal, the microbial agent expansion and automatic dosing equipment will not be regulated; if the working state of the microbial agent expansion and automatic dosing equipment is abnormal, a recommended regulation plan is generated, and the microbial agent expansion and automatic dosing equipment is regulated.

[0068] The characteristic parameters include the temperature, dissolved oxygen, pH, stirring speed, water addition amount and foam amount of the activation tank; the stirring speed and metering pump discharge flow rate of the liquid storage tank; the bacteria addition amount, tap water amount, stirring speed and high-pressure pump discharge flow rate of the dilution tank.

[0069] Among them, the preset control index requirements for microbial inoculant expansion and automatic dosing equipment refer to a series of key parameter standards and targets that are pre-set in the production process of microbial inoculants to ensure the quality and efficiency of expansion and dosing. These indicators usually cover temperature, pH value, dissolved oxygen concentration, nutrient supply rate, inoculant concentration and other aspects, which together constitute the ideal environmental conditions for microbial growth and reproduction.

[0070] It should be noted that, firstly, by presetting the control index requirements, the ideal parameter values ​​that the microbial agent expansion and automatic dosing equipment should reach at each key time node are determined. This step ensures the target and standardization of the equipment operation and provides a clear reference benchmark for subsequent data collection and analysis. Next, during the operation of the equipment, the actual parameter values ​​of each characteristic parameter are collected in sequence at the preset time nodes and stored in the data repository, so as to realize the real-time monitoring of the equipment operation status. The data accumulation in this link provides a rich and continuous basis for the subsequent status evaluation. After the parameter data in the data repository is classified and processed, the actual values ​​of various parameters are output. By comparing the preset value with the actual value, the operating status of the equipment at each preset time node can be intuitively evaluated, so as to obtain the overall working status of the equipment. Based on the analysis of the actual parameter value, it can be judged whether the equipment is in a normal or abnormal state. If the state is normal, no additional control processing is required to avoid unnecessary intervention. However, once an abnormal state is detected, the system will generate a recommended control scheme and immediately initiate the corresponding control measures to correct the deviation from the preset target and ensure that the equipment operates in the optimal state. The entire control process realizes the refined management and real-time monitoring of the microbial agent expansion and automatic dosing equipment through automation, which significantly improves the operating efficiency and stability of the equipment. At the same time, through intelligent analysis and rapid response mechanism, it effectively prevents potential operating problems and reduces losses caused by equipment abnormalities, providing strong technical support for the efficient production and quality control of microbial agents, and realizing the comprehensive monitoring and management process of microbial agent expansion and automatic dosing equipment, aiming to ensure the efficient and stable operation of the equipment during the working process.

[0071] More specifically, the characteristic parameters in the data repository are classified and processed, and the classification results are output, specifically:

[0072] Constructing a grid system, dividing the grid system into a plurality of sub-grid spaces, obtaining characteristic parameters in a data storage repository, and mapping the characteristic parameters in the data storage repository to each sub-grid space respectively;

[0073] Acquire text features of feature parameters in each sub-grid space, and calculate mutual information values ​​between feature parameters in each sub-grid space based on the text features of feature parameters in each sub-grid space;

[0074] The feature parameters whose mutual information values ​​are greater than a preset threshold are marked as strongly associated feature parameters, and the sub-grid spaces to which the feature parameters whose mutual information values ​​are greater than the preset threshold belong are merged, so as to aggregate all the feature parameters marked as strongly associated to obtain several aggregated spaces; wherein each aggregated space aggregates feature parameters with information sharing;

[0075] Calculate the mean of all characteristic parameters in each aggregation space, and determine the aggregation center of each aggregation space according to the calculated mean;

[0076] Calculate the Manhattan distance from all feature parameters in each aggregation space to the aggregation center, square the Manhattan distance from all feature parameters in each aggregation space to the aggregation center, and obtain the contribution value of each feature parameter to the discreteness of the aggregation space to which it belongs;

[0077] The contribution values ​​of all characteristic parameters in each aggregation space are added together to obtain the total dispersion of each aggregation space. The total dispersion of each aggregation space is divided by the total number of all characteristic parameters in the aggregation space to obtain the average dispersion of each aggregation space.

[0078] The average discreteness of each aggregation space is compared with the preset discreteness threshold; if the average discreteness of an aggregation space is greater than the preset discreteness threshold, the aggregation space is marked as a high-variance space; if the average discreteness of an aggregation space is not greater than the preset discreteness threshold, the aggregation space is marked as a low-variance space;

[0079] De-noising the aggregation space marked as a high-variance space to obtain a denoised aggregation space, and performing time series-based sorting on the characteristic parameters in the denoised aggregation space;

[0080] The aggregation space marked as low-variance space is not subjected to denoising, and the characteristic parameters in the aggregation space that is not subjected to denoising are sorted based on time series;

[0081] After processing, the classification results are output.

[0082] The mutual information value ranges from 0 to infinity, and the larger the value, the higher the correlation between the two feature parameters. If the mutual information is 0, it means that there is no information sharing between the two feature parameters, that is, they are independent; if the mutual information is close to infinity, it means that there is a strong correlation between the two feature parameters.

[0083] It should be noted that first, by constructing a grid system and dividing it into sub-grid spaces, complex data sets are decomposed into parts that are easier to understand and analyze. This structured approach helps capture the interdependence between different parameters. Then, by calculating the mutual information value between the feature parameters in each sub-grid space, the feature parameters with strong correlation are identified, and then aggregation processing is performed to form an aggregate space for information sharing. This method helps to reveal the intrinsic connection between parameters and provides a basis for subsequent analysis. Furthermore, by calculating the mean of the feature parameters in the aggregate space and the Manhattan distance to the aggregation center, the concentration and distribution of the parameters are quantified, and then the average dispersion of each aggregate space is calculated. This step helps to distinguish between spaces with high variability (i.e., high variability spaces) and spaces with low variability (i.e., low variability spaces). For high variability spaces, denoising is used to remove noise interference and improve the purity and reliability of the data; for low variability spaces, sorting is performed directly. Finally, through this series of analysis and processing, the classification results of the feature parameters in the data repository can be obtained, that is, the division of high variability spaces and low variability spaces. This not only helps to understand the stability of equipment operation and potential problem areas, but also provides a scientific basis for optimizing equipment operating parameters and improving production efficiency and product quality.

[0084] In general, this method is used to classify the characteristic parameters in the data repository. For example, the collected stirring speed of the liquid storage tank is classified into a data set, and it is sorted based on the time characteristics of the collection time, so as to obtain the actual parameter values ​​of each characteristic parameter in the microbial inoculant expansion and automatic dosing equipment at several preset time nodes. This can improve the monitoring accuracy of the operating status of the microbial inoculant expansion and automatic dosing equipment, enhance the prediction ability and response speed of equipment abnormalities, and help to achieve stable operation and optimized control of the equipment.

[0085] More specifically, the aggregation space marked as high-variance space is denoised to obtain the denoised aggregation space, which is:

[0086] Obtain all aggregate spaces marked as high-variance spaces, and define them as aggregate spaces to be denoised;

[0087] The DBSCAN algorithm is introduced, and the neighborhood radius and the minimum number of samples are preset; the aggregation space to be denoised is obtained, and the total number of feature parameters of each feature parameter in the aggregation space to be denoised within the preset domain radius is calculated;

[0088] Compare the total number of feature parameters of each feature parameter within the preset domain radius with the minimum number of samples;

[0089] If the total number of feature parameters of a certain feature parameter within the preset domain radius is greater than or equal to the minimum number of samples, the feature parameter is marked as a density-reachable feature parameter of the aggregation space to be denoised;

[0090] If the total number of feature parameters of a certain feature parameter within the preset domain radius is less than the minimum number of samples, the feature parameter is marked as a non-density-reachable feature parameter of the aggregation space to be denoised;

[0091] By analogy, the non-density-reachable characteristic parameters of each aggregation space to be denoised are detected based on the DBSCAN algorithm;

[0092] The non-density-reachable feature parameters in each aggregation space to be denoised are screened out to obtain the denoised aggregation space.

[0093] It should be noted that, first, the aggregation space that needs to be denoised is screened out from all the aggregation spaces marked as high-variance spaces, which is defined as the "aggregation space to be denoised". Then, the DBSCAN algorithm is introduced, and the neighborhood radius and the minimum number of samples are preset as key parameters. This step lays the foundation for the subsequent denoising process. Next, by calculating the total number of feature parameters of each feature parameter within the preset domain radius and comparing it with the minimum number of samples, if the total number of feature parameters of a feature parameter within the preset domain radius is greater than or equal to the minimum number of samples, it is considered that the feature parameter is sufficiently representative and is marked as the "density-reachable feature parameter of the aggregation space to be denoised". On the contrary, if the total number of feature parameters of the feature parameter within the preset domain radius is less than the minimum number of samples, it is marked as the "non-density-reachable feature parameter of the aggregation space to be denoised". In this way, feature parameters with insufficient sample numbers within a specific domain can be systematically identified and screened out from the aggregation space to obtain the denoised aggregation space. This process helps to remove noise interference, enhance the representativeness and accuracy of the data, and realize the refined denoising of characteristic parameters in the high-variability space. It not only improves the quality, purity and reliability of the data, but also provides a more reliable basis for subsequent analysis and decision-making.

[0094] More specifically, if Figure 2 As shown, the characteristic parameters in the microbial agent expansion and automatic dosing equipment are analyzed according to the actual parameter values ​​and preset parameter values ​​of each characteristic parameter at several preset time nodes, and the working status of the microbial agent expansion and automatic dosing equipment is obtained by analysis, specifically:

[0095] S202: constructing a plurality of two-dimensional coordinate systems, and constructing actual parameter value curve graphs and preset parameter value curve graphs of each characteristic parameter according to actual parameter values ​​and preset parameter values ​​of each characteristic parameter at a plurality of preset time nodes in the corresponding two-dimensional coordinate systems;

[0096] S204: Calculate the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in each two-dimensional coordinate system; and compare the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in each two-dimensional coordinate system with a preset overlap rate threshold;

[0097] S206: If the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in a certain two-dimensional coordinate system is not greater than the preset overlap rate threshold, the corresponding characteristic parameter in the microbial inoculant expansion and automatic dosing equipment is calibrated as a drift characteristic parameter;

[0098] S208: If the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in a certain two-dimensional coordinate system is greater than the preset overlap rate threshold, the corresponding characteristic parameters in the microbial inoculant expansion and automatic dosing equipment are calibrated as normal characteristic parameters;

[0099] S210: Determine whether drift characteristic parameters appear in the microbial agent expansion and automatic dosing equipment; if drift characteristic parameters appear, mark the working state of the microbial agent expansion and automatic dosing equipment as an abnormal state; if no drift characteristic parameters appear, mark the working state of the microbial agent expansion and automatic dosing equipment as a normal state.

[0100] It should be noted that by constructing several two-dimensional coordinate systems, an independent coordinate system is set for each characteristic parameter, and then in each coordinate system, according to the actual parameter value and the preset parameter value at the preset time node, the actual parameter value curve graph and the preset parameter value curve graph are drawn. This step provides an intuitive visual reference for subsequent drift detection. Next, the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in each two-dimensional coordinate system is calculated, that is, the ratio of the coverage area of ​​the two curve graphs, which is a quantitative indicator to measure whether the characteristic parameter deviates from the preset value. Then, the calculated overlap rate is compared with the preset overlap rate threshold. If the overlap rate is lower than the threshold, it indicates that the fluctuation of the characteristic parameter is large and the degree of deviation from the preset value is high, so it is marked as a "drift characteristic parameter". On the contrary, if the overlap rate is higher than the threshold, it means that the fluctuation of the characteristic parameter is small and is relatively consistent with the preset value, so it is marked as a "normal characteristic parameter". Finally, by detecting all characteristic parameters, it is determined whether there is a drift characteristic parameter. If the presence of a drift characteristic parameter is detected, it means that the working state of the microbial inoculant expansion and automatic dosing equipment is abnormal and should be marked as "abnormal state". On the contrary, if no drift characteristic parameters are detected, it is marked as "normal state". For the identified drift characteristic parameters, the preset parameter values ​​can be adjusted according to the actual situation, the control strategy can be optimized, the stability and efficiency of equipment operation can be improved, and problems in equipment operation can be handled in a timely manner, which can effectively reduce production interruptions, improve production efficiency, and ensure the stability of product quality.

[0101] More specifically, if the working state of the microbial agent expansion and automatic dosing equipment is abnormal, a recommended control scheme is generated, and the microbial agent expansion and automatic dosing equipment is controlled, specifically:

[0102] Obtaining assembly drawing information of the microbial agent expansion and automatic dosing equipment, and constructing a three-dimensional model diagram of the equipment for the microbial agent expansion and automatic dosing equipment according to the assembly drawing information;

[0103] If the working state of the microbial agent expansion and automatic dosing equipment is abnormal, obtain the real-time parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment, integrate the real-time parameter values ​​of each characteristic parameter into the equipment three-dimensional model diagram using PROE software, and establish a real-time simulation model diagram of the microbial agent expansion and automatic dosing equipment;

[0104] If the working state of the microbial agent expansion and automatic dosing equipment is abnormal, the drift characteristic parameters in the microbial agent expansion and automatic dosing equipment are obtained at the same time;

[0105] Constructing search keywords based on the drift characteristic parameters in the microbial agent expansion and automatic dosing equipment, searching the shared database according to the search keywords, and retrieving several control schemes; and obtaining the control parameters of each control scheme;

[0106] PROE software is used to simulate and control the real-time simulation model diagram of microbial agent expansion and automatic dosing equipment based on the control parameters of each control scheme, and the simulation parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment after the simulation and control of each control scheme are obtained; and the control time required for the simulation and control of each control scheme is obtained.

[0107] The following steps are also included:

[0108] According to the control time required for the simulation control of each control scheme, the predicted working time node of the microbial agent expansion culture and automatic dosing equipment after the simulation control of each control scheme is determined;

[0109] Determine the standard parameter range value of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at the predicted working time node according to the preset control index requirements;

[0110] Determine whether the simulation parameter values ​​of each characteristic parameter in the microbial agent expansion culture and automatic dosing equipment after the simulation control of each control scheme are within the corresponding standard parameter range value;

[0111] Obtaining a control scheme in which all simulation parameter values ​​are within the corresponding standard parameter range values, and obtaining an energy consumption loss value of the control scheme in which all simulation parameter values ​​are within the corresponding standard parameter range values;

[0112] The control scheme with the lowest energy consumption loss value is taken as the recommended control scheme, and the microbial agent expansion culture and automatic dosing equipment are regulated according to the recommended control scheme.

[0113] Among them, the shared database refers to a comprehensive database system that integrates a large amount of information about the operation status, control strategies, performance optimization schemes, and related equipment parameters of microbial agent expansion and automatic dosing equipment. This database not only contains various parameter settings, operating instructions, historical operation data, etc. during normal operation of the equipment, but also includes a large number of equipment abnormalities and their corresponding solutions, control parameters, execution steps, expected effects, energy consumption analysis, etc. The role of the shared database is to provide a comprehensive and dynamic information resource platform for equipment managers, maintenance personnel, technicians, etc. to query, refer to and learn when encountering equipment operation problems. By searching keywords, users can quickly find control schemes related to the current problem in the database, saving time and cost, and improving the efficiency and accuracy of problem solving. At the same time, the historical data and case analysis in the database also provide valuable experience and theoretical basis for optimizing equipment operation strategies, predicting potential problems, and formulating preventive measures, which helps to improve the stability and production efficiency of the equipment, reduce operating costs, and achieve energy conservation and emission reduction and sustainable development.

[0114] It should be noted that by obtaining assembly drawing information and constructing a three-dimensional model diagram, visual management of the equipment is achieved. This step provides a basic framework for subsequent fault diagnosis, status monitoring and performance optimization. When the equipment is in an abnormal working state, the system can respond quickly, integrate the real-time parameter values ​​into the three-dimensional model diagram, and construct a real-time simulation model diagram. This process can not only intuitively display the current operating state of the equipment, but also quickly identify abnormal parameters by comparing the preset parameter values, providing a direct basis for subsequent fault location and problem analysis. After identifying the drift characteristic parameters, the system uses search keywords to find relevant control schemes in the shared database. These schemes contain specific control parameters. The real-time simulation model is simulated and controlled by PROE software to simulate the effects of various control strategies. This process not only verifies the feasibility of different control schemes, but also quantifies the control time required for each scheme, providing information on the time dimension for subsequent decision-making. The system further predicts the working time node of the regulated equipment based on the control time, and determines the standard parameter range of each characteristic parameter at the predicted working time node in combination with the preset control index requirements. By comparing the simulation parameter value with the standard parameter range, the control schemes whose parameter values ​​are all within the specified range are screened out, and their energy loss values ​​are calculated. Finally, the solution with the lowest energy consumption is selected as the recommended solution for actual regulation. This method realizes the full chain management from equipment status monitoring, fault diagnosis, solution optimization to actual regulation. Through virtual simulation, the complexity and risk of actual operation are reduced, and the scientificity and efficiency of decision-making are improved. At the same time, through energy consumption optimization, the green sustainability of production is promoted, which is in line with the trend of modern industrial development.

[0115] In addition, the control method further comprises the following steps:

[0116] Retrieve the lesion characteristic image information of the target microorganism when various lesion infections occur based on the big data network; construct a knowledge graph based on the lesion characteristic image information of the target microorganism after various bacterial infections occur; and regularly update the knowledge graph;

[0117] The culture area in the microbial agent expansion and automatic dosing equipment is disinfected by a disinfection mechanism, and after the disinfection, a preset amount of microbial agent is placed in the culture area for pre-culture;

[0118] After the pre-culture is completed, a microbial agent sample is obtained in the culture area, and actual characteristic image information of the target microorganism in the microbial agent sample is obtained based on an optical microscope;

[0119] Extracting characteristic image information of each lesion from the knowledge graph, and calculating a hash value between the actual characteristic image information and the characteristic image information of each lesion based on a perceptual hash algorithm to obtain a plurality of hash values;

[0120] Compare each hash value with the preset hash value; if each hash value is not greater than the preset hash value, it means that the sterilization of pathogens in the culture area meets the requirements, and the microbial agent expansion and automatic dosing equipment are officially put into operation;

[0121] If there is at least one hash value greater than the preset hash value, the microbial agent expansion and automatic dosing equipment is controlled to stop working; and a disinfection log of the disinfection mechanism disinfecting the culture area in the microbial agent expansion and automatic dosing equipment is obtained;

[0122] According to the disinfection log, the actual disinfection parameters of each sub-area in the culture area for disinfection by the disinfection mechanism are obtained; the actual disinfection parameters of each sub-area for disinfection are compared with the preset disinfection parameters to obtain the disinfection parameter difference between the actual disinfection parameters of each sub-area for disinfection and the preset disinfection parameters;

[0123] A sub-region where the disinfection parameter difference is greater than a preset parameter difference threshold is defined as a disinfection abnormality region, and the disinfection mechanism is corrected according to the disinfection abnormality region to improve the disinfection performance of the disinfection mechanism on the culture area.

[0124] It should be noted that through big data network retrieval and knowledge graph construction, the system can collect and integrate the characteristic image information of microbial agents under different lesion infection states, and build a comprehensive lesion feature database. The knowledge graph is updated regularly to ensure the timeliness and accuracy of the information, providing a solid foundation for subsequent image analysis. Secondly, disinfection is a key step to ensure that the growth environment of microbial agents is clean and harmless. The culture area is regularly disinfected by the disinfection mechanism to ensure that the growth environment of the microbial agent is free from pathogenic contamination. After disinfection, the pre-culture link simulates the real growth environment to provide a reliable starting point for the subsequent growth of the agent. The actual characteristic image information of the microbial agent sample obtained by the optical microscope is compared and analyzed with the lesion characteristic image information in the knowledge graph, and the hash value is calculated by the perceptual hash algorithm to achieve a rapid and accurate judgment of the growth state of the agent. The comparison result of the hash value is directly related to the sterilization of pathogens in the culture area, thereby determining whether the microbial agent expansion culture and automatic dosing equipment can be officially put into operation. Once at least one hash value greater than the preset hash value is detected, indicating that there is a potential risk of residual pathogens, the equipment will automatically stop working to avoid possible contamination risks. At this time, the system will record the disinfection log, track the specific operating parameters of the disinfection mechanism, including disinfection area, dosage, time, etc., compare with the preset disinfection parameters, and analyze the disinfection effect. For the difference between the actual disinfection parameters and the preset parameters, especially the sub-area where the difference in disinfection parameters exceeds the preset threshold, the system defines it as an abnormal disinfection area, and calibrates the disinfection mechanism accordingly to optimize the disinfection effect and ensure the comprehensive cleanliness and hygiene of the culture area, thereby improving the efficiency and safety of the entire production process. In general, this method not only realizes real-time monitoring and management of the growth environment of microbial agents, but also improves the autonomy and intelligence level of the equipment through technological innovation, effectively guarantees the production quality of microbial agents, and also improves the sustainability and environmental protection of the production process.

[0125] In addition, the control method further comprises the following steps:

[0126] Obtain the actual activity of the target microorganisms after microbial agent expansion and automatic dosing equipment expansion and dosing;

[0127] Obtaining preset control index requirements for microbial agent expansion and automatic dosing equipment, and determining preset parameter range values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment according to the preset control index requirements;

[0128] Analyzing and obtaining the linear relationship between the activity of the target microorganism and each characteristic parameter based on the grey correlation analysis method, and constructing a linear regression analysis model according to the linear relationship between the activity of the target microorganism and each characteristic parameter;

[0129] Importing the preset parameter range values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment into the linear regression analysis model for analysis, and obtaining the predicted activity of the target microorganism after the microbial agent expansion and automatic dosing equipment expansion and dosing;

[0130] If the actual activity of the target microorganism after the microbial agent expansion and automatic dosing equipment expansion and dosing is less than the predicted activity, the working status of the microbial agent expansion and automatic dosing equipment is analyzed;

[0131] If the working state of the microbial agent expansion and automatic dosing equipment is abnormal, a recommended control plan is generated, and the microbial agent expansion and automatic dosing equipment is controlled;

[0132] If the working state of the microbial agent expansion and automatic dosing equipment is normal, obtain a disinfection log of the disinfection mechanism disinfecting the culture area in the microbial agent expansion and automatic dosing equipment;

[0133] According to the disinfection log, the actual disinfection parameters of each sub-area in the culture area for disinfection by the disinfection mechanism are obtained; the actual disinfection parameters of each sub-area for disinfection are compared with the preset disinfection parameters to obtain the disinfection parameter difference between the actual disinfection parameters of each sub-area for disinfection and the preset disinfection parameters;

[0134] A sub-region where the disinfection parameter difference is greater than a preset parameter difference threshold is defined as a disinfection abnormality region, and the disinfection mechanism is corrected according to the disinfection abnormality region.

[0135] It should be noted that first, the actual activity of the target microorganism and the preset control index requirements of the equipment are obtained, and the preset parameter range values ​​of each characteristic parameter are determined. Then, a linear regression analysis model is constructed by the gray correlation analysis method to predict the activity of the target microorganism after the equipment is expanded and added. If the actual activity is less than the predicted activity, the working state of the equipment needs to be analyzed. If the working state is abnormal, a recommended control scheme is generated and controlled; if the working state is normal, the disinfection log of the disinfection mechanism is obtained, the actual disinfection parameters are compared with the preset disinfection parameters, and the sub-area with a difference greater than the threshold is defined as the abnormal disinfection area, and the disinfection mechanism is corrected. This is because the working state of the microbial agent expansion and automatic dosing equipment is normal. At this time, the low activity of the target microorganism is most likely caused by bacterial infection. Therefore, it is necessary to further trace the abnormal disinfection area at this time, so as to help timely discover and solve the problem of incomplete disinfection and ensure the hygiene and safety of the culture area. Correction of the disinfection mechanism can improve the effect and reliability of disinfection and ensure the quality and safety of microbial agents. The whole process is aimed at ensuring the expansion and addition effect of microbial agents, as well as the normal operation and disinfection effect of the equipment.

[0136] like Figure 2 As shown, the second aspect of the present invention discloses a control system for microbial agent expansion and automatic dosing equipment, the control system includes a memory 41 and a processor 62, the memory 41 stores a control method program for microbial agent expansion and automatic dosing equipment, when the control method program for microbial agent expansion and automatic dosing equipment is executed by the processor 62, the steps of any one of the control methods for microbial agent expansion and automatic dosing equipment are implemented.

[0137] The third aspect of the present invention discloses a computer-readable storage medium, which includes a control method program for microbial inoculant expansion and automatic dosing equipment. When the control method program for microbial inoculant expansion and automatic dosing equipment is executed by a processor, the steps of any one of the control methods for microbial inoculant expansion and automatic dosing equipment are implemented.

[0138] In addition, in order to make it easier to understand the control process of the microbial agent expansion and automatic dosing equipment, the work flow of the microbial agent expansion and automatic dosing equipment is briefly described, such as Figure 4 As shown, the microbial agent expansion and automatic dosing equipment consists of two paths:

[0139] (1) The first route: The bacterial liquid is pumped from the activation tank to the liquid storage tank through a pump, and then transported to the subsequent unit through a metering pump (flow rate 1 to 2 L / min, head 15 m, flow rate controllable).

[0140] (2) The second path: The bacterial liquid is pumped from the activation tank to the liquid storage tank through a pump, and then transported to the dilution tank through a metering pump. Tap water is added to the dilution tank in a quantitative manner. After the bacterial agent is quantitatively diluted, it is transported to the subsequent unit through a high-pressure pump (20MPa, 50L / min, with frequency conversion, flow and pressure controllable).

[0141] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A control method for microbial agent expansion and automatic dosing equipment, characterized in that: The following steps are involved: Obtaining preset control index requirements for microbial agent expansion and automatic dosing equipment, and determining preset parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at a number of preset time nodes according to the preset control index requirements; During the operation of the microbial agent expansion and automatic dosing equipment, the actual parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment are collected in sequence at a number of preset time nodes, and the actual parameter values ​​of the characteristic parameters collected are stored in a data storage library; After the collection is completed, the characteristic parameters in the data storage are classified and processed, and the classification results are output; according to the classification results, the actual parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at several preset time nodes are obtained; Analyze each characteristic parameter in the microbial agent expansion and automatic dosing equipment according to the actual parameter value and the preset parameter value of each characteristic parameter at several preset time nodes, and obtain the working status of the microbial agent expansion and automatic dosing equipment by analysis; If the working state of the microbial agent expansion and automatic dosing equipment is normal, the microbial agent expansion and automatic dosing equipment is not regulated; if the working state of the microbial agent expansion and automatic dosing equipment is abnormal, a recommended regulation scheme is generated, and the microbial agent expansion and automatic dosing equipment is regulated; Among them, the characteristic parameters in the data repository are classified and processed, and the classification results are output, specifically: Constructing a grid system, dividing the grid system into a plurality of sub-grid spaces, obtaining characteristic parameters in a data storage repository, and mapping the characteristic parameters in the data storage repository to each sub-grid space respectively; Acquire text features of feature parameters in each sub-grid space, and calculate mutual information values ​​between feature parameters in each sub-grid space based on the text features of feature parameters in each sub-grid space; The feature parameters whose mutual information values ​​are greater than a preset threshold are marked as strongly associated feature parameters, and the sub-grid spaces to which the feature parameters whose mutual information values ​​are greater than the preset threshold belong are merged, so as to aggregate all the feature parameters marked as strongly associated to obtain several aggregated spaces; wherein each aggregated space aggregates feature parameters with information sharing; Calculate the mean of all characteristic parameters in each aggregation space, and determine the aggregation center of each aggregation space according to the calculated mean; Calculate the Manhattan distance from all feature parameters in each aggregation space to the aggregation center, square the Manhattan distance from all feature parameters in each aggregation space to the aggregation center, and obtain the contribution value of each feature parameter to the discreteness of the aggregation space to which it belongs; The contribution values ​​of all characteristic parameters in each aggregation space are added together to obtain the total dispersion of each aggregation space. The total dispersion of each aggregation space is divided by the total number of all characteristic parameters in the aggregation space to obtain the average dispersion of each aggregation space. The average discreteness of each aggregation space is compared with the preset discreteness threshold; if the average discreteness of an aggregation space is greater than the preset discreteness threshold, the aggregation space is marked as a high-variance space; if the average discreteness of an aggregation space is not greater than the preset discreteness threshold, the aggregation space is marked as a low-variance space; De-noising the aggregation space marked as a high-variance space to obtain a denoised aggregation space, and performing time series-based sorting on the characteristic parameters in the denoised aggregation space; The aggregation space marked as low-variance space is not subjected to denoising, and the feature parameters in the aggregation space that is not subjected to denoising are sorted based on time series. After processing, the classification results are output.

2. The control method of a microbial agent expansion and automatic dosing equipment according to claim 1, characterized in that: The aggregation space marked as high-variance space is denoised to obtain the denoised aggregation space, which is: Obtain all aggregate spaces marked as high-variance spaces, and define them as aggregate spaces to be denoised; The DBSCAN algorithm is introduced, and the neighborhood radius and the minimum number of samples are preset; the aggregation space to be denoised is obtained, and the total number of feature parameters of each feature parameter in the aggregation space to be denoised within the preset domain radius is calculated; Compare the total number of feature parameters of each feature parameter within the preset domain radius with the minimum number of samples; If the total number of feature parameters of a certain feature parameter within the preset domain radius is greater than or equal to the minimum number of samples, the feature parameter is marked as a density-reachable feature parameter of the aggregation space to be denoised; If the total number of feature parameters of a certain feature parameter within the preset domain radius is less than the minimum number of samples, the feature parameter is marked as a non-density-reachable feature parameter of the aggregation space to be denoised; By analogy, the non-density-reachable characteristic parameters of each aggregation space to be denoised are detected based on the DBSCAN algorithm; The non-density-reachable feature parameters in each aggregation space to be denoised are screened out to obtain the denoised aggregation space.

3. The control method of a microbial agent expansion and automatic dosing equipment according to claim 1, characterized in that: According to the actual parameter values ​​and preset parameter values ​​of each characteristic parameter at several preset time nodes, each characteristic parameter in the microbial agent expansion and automatic dosing equipment is analyzed, and the working status of the microbial agent expansion and automatic dosing equipment is obtained by analysis, specifically: Constructing a plurality of two-dimensional coordinate systems, and constructing actual parameter value curve graphs and preset parameter value curve graphs of each characteristic parameter according to actual parameter values ​​and preset parameter values ​​of each characteristic parameter at a plurality of preset time nodes in the corresponding two-dimensional coordinate systems; Calculating the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in each two-dimensional coordinate system; and comparing the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in each two-dimensional coordinate system with a preset overlap rate threshold; If the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in a certain two-dimensional coordinate system is not greater than the preset overlap rate threshold, the corresponding characteristic parameter in the microbial inoculant expansion and automatic dosing equipment is calibrated as a drift characteristic parameter; If the overlap rate between the actual parameter value curve graph and the preset parameter value curve graph in a certain two-dimensional coordinate system is greater than the preset overlap rate threshold, the corresponding characteristic parameters in the microbial inoculant expansion and automatic dosing equipment are calibrated as normal characteristic parameters; Determine whether drift characteristic parameters appear in the microbial agent expansion and automatic dosing equipment; if drift characteristic parameters appear, mark the working status of the microbial agent expansion and automatic dosing equipment as abnormal; if no drift characteristic parameters appear, mark the working status of the microbial agent expansion and automatic dosing equipment as normal.

4. The control method of a microbial agent expansion and automatic dosing equipment according to claim 1, characterized in that: If the working state of the microbial agent expansion and automatic dosing equipment is abnormal, a recommended control plan is generated, and the microbial agent expansion and automatic dosing equipment is controlled, specifically: Obtaining assembly drawing information of the microbial agent expansion and automatic dosing equipment, and constructing a three-dimensional model diagram of the equipment for the microbial agent expansion and automatic dosing equipment according to the assembly drawing information; If the working state of the microbial agent expansion and automatic dosing equipment is abnormal, obtain the real-time parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment, integrate the real-time parameter values ​​of each characteristic parameter into the equipment three-dimensional model diagram using PROE software, and establish a real-time simulation model diagram of the microbial agent expansion and automatic dosing equipment; If the working state of the microbial agent expansion and automatic dosing equipment is abnormal, the drift characteristic parameters in the microbial agent expansion and automatic dosing equipment are obtained at the same time; Constructing search keywords based on the drift characteristic parameters in the microbial agent expansion and automatic dosing equipment, searching the shared database according to the search keywords, and retrieving several control schemes; and obtaining the control parameters of each control scheme; Using PROE software and based on the control parameters of each control scheme, the real-time simulation model diagram of the microbial agent expansion and automatic dosing equipment is simulated and controlled, and the simulation parameter values ​​of each characteristic parameter in the microbial agent expansion and automatic dosing equipment after the simulation and control of each control scheme are obtained; And obtain the control time required for simulation control of each control scheme.

5. The control method of a microbial agent expansion and automatic dosing equipment according to claim 4, characterized in that: The following steps are also included: According to the control time required for the simulation control of each control scheme, the predicted working time node of the microbial agent expansion culture and automatic dosing equipment after the simulation control of each control scheme is determined; Determine the standard parameter range value of each characteristic parameter in the microbial agent expansion and automatic dosing equipment at the predicted working time node according to the preset control index requirements; Determine whether the simulation parameter values ​​of each characteristic parameter in the microbial agent expansion culture and automatic dosing equipment after the simulation control of each control scheme are within the corresponding standard parameter range value; Obtaining a control scheme in which all simulation parameter values ​​are within the corresponding standard parameter range values, and obtaining an energy consumption loss value of the control scheme in which all simulation parameter values ​​are within the corresponding standard parameter range values; The control scheme with the lowest energy consumption loss value is taken as the recommended control scheme, and the microbial agent expansion culture and automatic dosing equipment are regulated according to the recommended control scheme.

6. The control method of a microbial agent expansion and automatic dosing equipment according to claim 1, characterized in that: The characteristic parameters include the temperature of the activation tank, dissolved oxygen, pH, stirring speed, water addition amount and foam amount; The characteristic parameters also include the stirring speed of the liquid storage tank and the discharge flow rate of the metering pump; The characteristic parameters also include the amount of bacteria added to the dilution tank, the amount of tap water, the stirring speed, and the discharge flow rate of the high-pressure pump.

7. A control system for microbial agent expansion and automatic dosing equipment, characterized in that: The control system includes a memory and a processor, wherein the memory stores a control method program for the microbial agent expansion and automatic dosing equipment. When the control method program for the microbial agent expansion and automatic dosing equipment is executed by the processor, the steps of the control method for the microbial agent expansion and automatic dosing equipment as described in any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a control method program for microbial inoculant expansion and automatic dosing equipment. When the control method program for microbial inoculant expansion and automatic dosing equipment is executed by a processor, the steps of the control method for microbial inoculant expansion and automatic dosing equipment as described in any one of claims 1 to 6 are implemented.

Images