Method and system for intelligently regulating and controlling production pressure of aerated concrete blocks

Abstract

The invention discloses an aerated concrete block production pressure intelligent regulation and control method and system, and relates to the technical field of intelligent control. The method comprises the steps that slurry is injected into a forming mold, meanwhile, a pressure sensor array is activated to conduct data collection, and a pressure data array sequence is obtained; calling a temperature sensor and a flow sensor to perform synchronous sensing in combination with a timestamp to obtain a temperature data sequence and a flow data sequence which are synchronously mapped; carrying out reaction stage identification, and determining a first reaction stage; and based on the pressure regulation and control target of the first reaction stage, optimizing and adjusting the current real-time pressure control parameter, determining a target pressure adjustment parameter, and regulating and controlling the production pressure according to the target pressure adjustment parameter. The technical problem that in the prior art, in the aerated concrete block production process, dynamic pressure regulation and control are difficult according to the reaction stage, and consequently the block quality is unstable is solved, and the technical effects that intelligent pressure regulation and control are achieved based on the reaction stage, and the block forming quality is improved are achieved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, specifically to an intelligent control method and system for the production pressure of aerated concrete blocks. Background Technology

[0002] Autoclaved aerated concrete (AAC) blocks, as a lightweight, heat-insulating, and environmentally friendly building material, are widely used in various construction projects. During the production of AAC blocks, the mortar undergoes complex physicochemical reactions in the mold, such as gas generation, expansion, and initial setting. Different stages require different molding pressures. In traditional production methods, pressure control often relies on fixed parameter settings or manual experience, making it difficult to dynamically adjust according to the actual reaction state. This can easily lead to delayed or excessive pressure control, affecting the density, strength, and dimensional accuracy of the blocks, and restricting the consistency and stability of product quality. Summary of the Invention

[0003] This application provides a method and system for intelligent control of pressure in the production of aerated concrete blocks, which solves the technical problem in the prior art that it is difficult to dynamically control the pressure according to the reaction stage during the production of aerated concrete blocks, resulting in unstable block quality.

[0004] The first aspect of this application provides a method for intelligent control of production pressure in aerated concrete block manufacturing, the method comprising: Slurry is injected into the molding die, and simultaneously, an array of pressure sensors deployed on the inner cavity of the molding die is activated to collect pressure change data, obtaining a pressure data array sequence, wherein each pressure data has a corresponding timestamp; temperature sensors and flow sensors are invoked in conjunction with the timestamps for synchronous sensing, obtaining synchronously mapped temperature data sequences and flow data sequences; based on the pressure data array sequence, temperature data sequence, and flow data sequence, reaction stage identification is performed to determine the first reaction stage; based on the pressure control target of the first reaction stage, the current real-time pressure control parameters are optimized and adjusted to determine the target pressure adjustment parameters, and production pressure is controlled according to the target pressure adjustment parameters.

[0005] A second aspect of this application provides an intelligent pressure control system for aerated concrete block production, the system comprising: The data acquisition module is used to inject slurry into the molding die and simultaneously activate the pressure sensor array deployed on the inner cavity of the molding die to collect pressure change data and obtain a pressure data array sequence, wherein each pressure data has a corresponding timestamp; the sensing module is used to call the temperature sensor and flow sensor in combination with the timestamp for synchronous sensing and obtain synchronously mapped temperature data sequence and flow data sequence; the identification module is used to identify the reaction stage based on the pressure data array sequence, temperature data sequence and flow data sequence to determine the first reaction stage; the control module is used to optimize and adjust the current real-time pressure control parameters based on the pressure control target of the first reaction stage, determine the target pressure adjustment parameter, and control the production pressure according to the target pressure adjustment parameter.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: Slurry is injected into the molding die, simultaneously activating an array of pressure sensors deployed within the die cavity to collect pressure change data, resulting in a pressure data array sequence. Each pressure data point has a corresponding timestamp. Simultaneously, temperature and flow sensors, combined with the timestamps, are used for synchronous sensing, obtaining synchronously mapped temperature and flow data sequences. Then, based on the pressure, temperature, and flow data sequences, the reaction stage is identified, determining the first reaction stage. Finally, based on the pressure control target of the first reaction stage, the current real-time pressure control parameters are optimized and adjusted to determine the target pressure adjustment parameters, and production pressure is controlled according to these parameters. This solves the technical problem in existing technologies where it is difficult to dynamically control pressure according to the reaction stage during aerated concrete block production, leading to unstable block quality. It achieves the technical effect of intelligent pressure control based on the reaction stage, improving the quality of block molding. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 A schematic diagram of the intelligent pressure control method for aerated concrete block production provided in this application embodiment; Figure 2 A schematic diagram of the intelligent control system for the production pressure of aerated concrete blocks provided in this application embodiment.

[0009] Explanation of reference numerals in the attached diagram: Data acquisition module 11, sensing module 12, identification module 13, control module 14. Detailed Implementation

[0010] This application provides an intelligent pressure control method and system for aerated concrete block production, which solves the technical problem in the prior art that it is difficult to dynamically control the pressure according to the reaction stage during the production of aerated concrete blocks, resulting in unstable block quality.

[0011] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0012] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0013] Example 1, as Figure 1 As shown, this application provides a method for intelligent control of production pressure in aerated concrete block manufacturing, wherein the method includes: Slurry is injected into the molding die, and at the same time, the pressure sensor array deployed on the inner cavity of the molding die is activated to collect pressure change data and obtain a pressure data array sequence, wherein each pressure data has a corresponding timestamp.

[0014] In this embodiment, the pressure sensor array on the mold cavity is activated simultaneously with the injection of aerated concrete slurry into the molding die, initiating a pressure data acquisition process. Each pressure sensor records the slurry pressure value at its location at a set sampling frequency (e.g., 10 times per second or higher), and binds this value to the current time, thus forming a pressure data point with a timestamp. The data from all pressure sensors together constitute a pressure data array sequence, which reflects the pressure change trend of the slurry in the mold cavity from injection to the reaction process, providing basic data support for subsequent reaction stage identification and dynamic pressure control.

[0015] Furthermore, injecting slurry into the molding die while simultaneously activating an array of pressure sensors deployed within the mold cavity to collect pressure change data includes: The center position of the bottom of the mold cavity and the center position of the top cover of the mold cavity are taken as the main pressure point set; the edge pressure point set is obtained by identifying the edge pressure point set based on the historical production log set; pressure sensors are deployed at the main pressure point set and the edge pressure point set respectively to obtain the pressure sensor array.

[0016] Preferably, the center of the bottom of the mold cavity and the center of the top cover of the mold cavity are where the pressure is most concentrated during the slurry injection and gas expansion process, which can reflect the main trend of the stress on the slurry. Therefore, the center of the bottom of the mold cavity and the center of the top cover of the mold cavity are determined as the main pressure point set. Based on the historical production log set (including the recorded data of pressure fluctuations in different parts of past batches of products), the pressure change distribution inside the mold cavity is modeled by data mining or statistical analysis methods to identify the edge areas that are prone to local pressure anomalies or fluctuations, and these are determined as the edge pressure point set. This set may include the four corner areas of the mold cavity, the junction of the side wall and the bottom plate, etc.

[0017] High-sensitivity pressure sensors are deployed at both the main pressure point set and the edge pressure point set, forming a pressure sensor array covering the key areas of the mold cavity. This sensor array can monitor multi-point pressure changes of the slurry in real time during injection and reaction, generating a pressure data array sequence with timestamps, providing accurate data support for subsequent reaction stage identification and intelligent pressure control.

[0018] Furthermore, edge stress point identification is performed based on historical production log sets to obtain a set of edge stress points, including: Data retrieval is performed on the historical production log set according to the location of the monitored pressure points and the corresponding pressure change data to obtain a set of monitored pressure point locations and a set of monitored pressure change data. Using the same monitored pressure point location as an index, cluster analysis is performed on the monitored pressure change data sets to determine Q clustered monitored pressure change data sets, where Q is an integer greater than or equal to 1. Based on the Q clustered monitored pressure change data sets, overall fluctuation coefficient analysis is performed to determine Q overall fluctuation coefficients. It is then determined whether the Q overall fluctuation coefficients are greater than or equal to a preset fluctuation coefficient threshold; if so, they are added to the edge pressure point set.

[0019] Preferably, based on the location of the monitored pressure points and the corresponding pressure change data, multiple batches of production data recorded in the historical production log set are retrieved to extract entries containing pressure monitoring information, thereby obtaining a set of monitored pressure point locations and a set of monitored pressure change data. The pressure monitoring information includes the location of the monitored pressure points and the corresponding pressure change data. Using the same monitored pressure point location as an index, cluster analysis is performed on the monitored pressure change data set, that is, cluster analysis is performed on multiple historical pressure change data at that location. Clustering algorithms such as K-means, DBSCAN, and hierarchical clustering can be used to cluster the historical data corresponding to the monitored point. Pressure change data is divided into Q cluster monitoring pressure change data sets, where Q is an integer greater than or equal to 1. An overall fluctuation coefficient analysis is performed on the Q cluster monitoring pressure change data sets. The overall fluctuation coefficient can be calculated using statistical indicators such as the coefficient of variation or standard deviation to assess the intensity of pressure fluctuations within different clusters at a given point, ultimately obtaining Q overall fluctuation coefficients. These Q overall fluctuation coefficients are compared with a preset fluctuation coefficient threshold. If the overall fluctuation coefficient of any cluster at a given monitoring point is greater than or equal to the preset threshold, the monitoring point is determined to have significant pressure uncertainty or sensitivity, and is added to the set of marginal pressure points.

[0020] Furthermore, based on the Q cluster monitoring pressure change data sets, an overall fluctuation coefficient analysis is performed to determine Q overall fluctuation coefficients, including: The data change rate is identified by traversing the Q cluster monitoring pressure change data sets to determine Q sets of data change rate sets. The mean of the Q sets of data change rate sets is calculated to obtain Q mean data change rates, and Q mean neighborhoods of the Q mean data change rates are constructed based on a preset neighborhood radius. The Q mean neighborhoods are expanded according to the preset neighborhood radius to obtain Q expanded mean neighborhoods. It is determined whether the neighborhood density of the Q expanded mean neighborhoods is greater than or equal to the neighborhood density of the Q mean neighborhoods. If so, the edges of the Q expanded mean neighborhoods are expanded according to the preset neighborhood radius until a preset stopping condition is met to obtain Q analytical expanded mean neighborhoods. The mean of the data change rate within the Q analytical expanded mean neighborhoods is calculated to obtain the Q overall fluctuation coefficients.

[0021] Preferably, the process involves traversing each of the Q cluster monitoring pressure change data sets, identifying the data change rate for each pressure change curve within the cluster, and calculating the data change rate by dividing the pressure difference between adjacent time points by the time difference to form a corresponding change rate set, thus obtaining Q data change rate sets. The mean of each data change rate set is then calculated to obtain Q mean data change rates. Using each mean data change rate as the center, Q initial mean neighborhoods are constructed based on a preset neighborhood radius parameter (e.g., a range set according to the absolute rate value or standard deviation). Each initial mean neighborhood represents a set of values ​​within a preset rate deviation range centered on the current mean rate. Finally, a neighborhood expansion operation is performed on the Q mean neighborhoods, i.e., expanding the neighborhoods beyond the initial neighborhoods based on the same neighborhood radius standard. The surrounding adjacent data range is expanded to form Q expanded mean neighborhoods. During this process, it is determined in real time whether the density of the expanded neighborhood (i.e., the number of data points contained in a unit value interval) is greater than or equal to the neighborhood density of the original mean neighborhood. If this condition is met, the expansion is deemed effective, and the same edge expansion strategy is continued. The above edge expansion operation continues until the preset stopping conditions are met, such as the expansion rounds reaching the upper limit, the neighborhood density growth stabilizing, or the rate of change falling below a threshold. At this point, the final Q analytical expanded mean neighborhoods are obtained. The data change rate values ​​contained in each analytical expanded mean neighborhood are statistically analyzed, and their mean is calculated as the overall fluctuation coefficient of the corresponding cluster. The overall fluctuation coefficient can comprehensively reflect the rate fluctuation intensity of the pressure change process within the cluster, serving as a key basis for determining whether the monitoring point is an edge pressure point.

[0022] Furthermore, the preset stopping condition is that the number of expansions meets the preset number of expansions or the difference in neighborhood density between two adjacent expansions is less than or equal to the preset neighborhood density difference threshold.

[0023] The preset stopping conditions include reaching a preset upper limit for the number of expansions. This upper limit can be set based on historical experience or system response timeliness to prevent excessive expansion from wasting computing resources or blurring the neighborhood. The preset stopping conditions also include that, in two consecutive expansion processes, the difference between the neighborhood density of the expanded neighborhood and the neighborhood density of the previous expansion is less than or equal to a preset neighborhood density difference threshold. The neighborhood density difference is used to reflect the change in the density of newly added data points after expansion. When this change tends to be stable or not significant, it indicates that the neighborhood has approached saturation and expansion can be stopped.

[0024] The temperature sensor and flow sensor are used in conjunction with timestamps for synchronous sensing to obtain synchronously mapped temperature data sequences and flow data sequences.

[0025] While the slurry is injected into the mold and pressure data is collected, temperature and flow sensors installed in the molding mold are also invoked to sense the temperature and flow status in real time during the slurry injection and initial reaction process, obtaining synchronously mapped temperature and flow data sequences. The temperature sensors can be installed on the mold cavity wall, slurry inlet pipe, or mold internal environment monitoring location, while the flow sensors are installed in the slurry supply pipe to measure the instantaneous flow rate or cumulative flow rate of the slurry entering the mold in real time.

[0026] Based on the pressure data array sequence, temperature data sequence, and flow rate data sequence, the reaction stage is identified to determine the first reaction stage.

[0027] Based on the synchronization timestamp, features such as pressure change rate, temperature change gradient, and flow fluctuation amplitude within the corresponding time period are extracted to form a multi-dimensional feature vector sequence for stage identification. The multi-dimensional feature vector sequence is matched with the preset reaction stage identification rule base to determine the current reaction stage of the slurry and output the identification result, which is identified as the first reaction stage.

[0028] Furthermore, based on the pressure data array sequence, temperature data sequence, and flow rate data sequence, reaction stage identification is performed to determine the first reaction stage, including: The pressure data array sequence, temperature data sequence, and flow data sequence are traversed to identify data change trend features, thereby obtaining pressure data change trend feature array, temperature data change trend features, and flow data change trend features. The pressure data change trend feature array is subjected to interactive fusion analysis to determine the fused pressure data change trend features. Based on the fused pressure data change trend features, temperature data change trend features, and flow data change trend features, reaction stage identification is performed to determine the first reaction stage.

[0029] Preferably, the pressure data array sequence, temperature data sequence, and flow rate data sequence are traversed, and a data change trend feature identification operation is performed for each type of data. The trend feature identification can be based on methods such as first derivative (rate of change), local extreme point extraction, trend slope calculation, and moving average offset to quantify the characteristics such as the direction, rate, and magnitude of data change. The feature identification results include pressure data change trend feature array, temperature data change trend feature, and flow rate data change trend feature. The pressure data change trend feature array is generated based on time-series data from multiple pressure sensing points within the mold cavity, reflecting the consistency or difference of pressure changes at different spatial locations. The temperature data change trend feature describes the rate of temperature change over time, trend stability, and inflection point behavior. The flow rate data change trend feature reflects the volatility, stability, or termination state of the slurry injection process.

[0030] Based on methods such as feature normalization, principal component analysis (PCA), and extraction of aggregated statistics (such as mean, range, variance, etc.), an interactive fusion analysis is performed on the pressure data change trend feature array to extract fused pressure data change trend features that can represent the dynamic change behavior of the overall pressure field. These fused features can be used to reflect key physical states such as the overall reaction rate, expansion degree, and spatial consistency within the slurry.

[0031] Based on the fused trends in pressure, temperature, and flow rates, a reaction stage identification model is invoked for joint discrimination. This model is rule-driven (e.g., rising temperature and rapidly increasing pressure correspond to the "gas generation stage"; flow rate approaching zero and pressure remaining high correspond to the "condensation stage"). The model outputs the reaction stage corresponding to the current moment, which is determined as the first reaction stage.

[0032] Furthermore, interactive fusion analysis is performed on the pressure data change trend feature array to determine the fused pressure data change trend features, including: Without replacement, randomly extract any two pressure data change trend features from the pressure data change trend feature array and perform feature interaction fusion to determine the first interactive pressure data change trend feature; then, without replacement, randomly extract another pressure data change trend feature and perform feature interaction fusion with the first interactive pressure data change trend feature to obtain the second interactive pressure data change trend feature; after multiple fusions, obtain the fused pressure data change trend feature.

[0033] Two pressure data trend features are randomly selected from the pressure data trend feature array using a non-replacement random sampling method. Feature interaction fusion is then performed, specifically based on feature overlay, vector weighted averaging, local convolution, maximum / minimum selection, or other non-linear combinations, to obtain a new set of interaction results, which serves as the first interactive pressure data trend feature. Another feature is randomly selected from the remaining unfused pressure data trend features without replacement, and this feature is subjected to the same interaction fusion process with the first interactive pressure data trend feature to generate the second interactive pressure data trend feature. The fusion process continues iteratively, with each round randomly selecting one unfused feature to interact with the previous round's fusion result, until all original pressure data trend features participate in the fusion, ultimately generating the fused pressure data trend feature.

[0034] Furthermore, this includes: Calculate the set of sub-feature similarity coefficients of two pressure data change trend features, and construct a first interaction matrix after normalization. Randomly perform convolution analysis between any one of the two pressure data change trend features and the first interaction matrix to obtain the first interactive pressure data change trend feature.

[0035] Preferably, for the two selected pressure data trend features, sub-feature sets are extracted from each. These sub-features may include, but are not limited to, rate of change, first-order difference value, local extremum location, trend slope, and normalized fluctuation intensity. The corresponding sub-features of these two features are compared one by one, and their similarity coefficients are calculated using methods such as Euclidean distance and cosine similarity to form a sub-feature similarity coefficient set. This sub-feature similarity coefficient set is then normalized to map all similarity values ​​to a unified numerical range (e.g., [0, 1]) to eliminate the influence of scale differences between different sub-features. Based on the normalization results, a first interaction matrix is ​​constructed. This matrix expresses the fusion relationship and interaction strength of the two pressure data trend features across multiple sub-dimensions. One of the two selected pressure data trend features is randomly selected as the basic feature input. This feature is then convolved with the first interaction matrix using one-dimensional convolution, local sliding weighting, or other methods to obtain the first interactive pressure data trend feature.

[0036] Based on the pressure control target of the first reaction stage, the current real-time pressure control parameters are optimized and adjusted to determine the target pressure adjustment parameters, and the production pressure is controlled according to the target pressure adjustment parameters.

[0037] After identifying the first reaction stage, the corresponding pressure control target parameter set is invoked based on the process requirements of this stage. Using this as a benchmark, the current real-time pressure control parameters are optimized and adjusted to determine the final target pressure adjustment parameters for execution, thereby achieving dynamic pressure control during the aerated concrete slurry reaction process. Specifically, based on the type of the first reaction stage (e.g., gas expansion stage, setting and stabilization stage), preset pressure control targets are queried, including target pressure values, upper / lower limits of pressure change rates, and fluctuation tolerance ranges. These pressure control targets can be derived from empirical rules, experimental models, or statistical results of historical high-quality batch process parameters. The current real-time pressure control parameters are then optimized and adjusted in conjunction with the pressure control targets to determine the target pressure adjustment parameters. Finally, production pressure is controlled based on these target pressure adjustment parameters.

[0038] Furthermore, a regulation feedback window is determined, and pressure is continuously monitored within the regulation feedback window to obtain a first regulation feedback result.

[0039] Based on the duration characteristics of the current reaction stage and parameters such as the slurry reaction rate, a continuous time interval is set as the adjustment feedback window. The adjustment feedback window can be a fixed duration (e.g., 5 seconds, 10 seconds) or an adaptive duration (e.g., terminating early after the pressure reaches a stable threshold). Within the adjustment feedback window, pressure change data within the mold cavity is continuously collected by a pressure sensor array, forming a pressure time sequence. Further statistical analysis of the pressure data within the feedback window is performed to evaluate whether the current adjustment action has achieved the expected pressure control target. Specifically, it can be determined whether the pressure is stable within the target value ± tolerance range, whether the pressure change rate is lower than the set threshold, and whether there are unstable phenomena such as over-adjustment / under-adjustment or violent fluctuations. Finally, the first adjustment feedback result is output to characterize the current adjustment effect. If the feedback result meets the control target requirements, the current control parameters are maintained; if the requirements are not met, the parameter re-optimization process can be automatically triggered, or error correction and compensation adjustments can be performed according to the control rules, thereby achieving closed-loop control.

[0040] In summary, the embodiments of this application have at least the following technical effects: Slurry is injected into the molding die, simultaneously activating an array of pressure sensors deployed within the die cavity to collect pressure change data, resulting in a pressure data array sequence. Each pressure data point has a corresponding timestamp. Simultaneously, temperature and flow sensors, combined with the timestamps, are used for synchronous sensing, obtaining synchronously mapped temperature and flow data sequences. Then, based on the pressure, temperature, and flow data sequences, the reaction stage is identified, determining the first reaction stage. Finally, based on the pressure control target of the first reaction stage, the current real-time pressure control parameters are optimized and adjusted to determine the target pressure adjustment parameters, and production pressure is controlled according to these parameters. This solves the technical problem in existing technologies where it is difficult to dynamically control pressure according to the reaction stage during aerated concrete block production, leading to unstable block quality. It achieves the technical effect of intelligent pressure control based on the reaction stage, improving the quality of block molding.

[0041] Example 2, based on the same inventive concept as the intelligent control method for aerated concrete block production pressure in the foregoing examples, such as... Figure 2 As shown, this application provides an intelligent control system for the production pressure of aerated concrete blocks, wherein the system includes: The data acquisition module 11 is used to inject slurry into the molding die and simultaneously activate the pressure sensor array deployed on the inner cavity of the molding die to collect pressure change data and obtain a pressure data array sequence, wherein each pressure data has a corresponding timestamp; the sensing module 12 is used to call the temperature sensor and flow sensor in combination with the timestamp for synchronous sensing and obtain synchronously mapped temperature data sequence and flow data sequence; the identification module 13 is used to identify the reaction stage based on the pressure data array sequence, temperature data sequence and flow data sequence to determine the first reaction stage; the control module 14 is used to optimize and adjust the current real-time pressure control parameters based on the pressure control target of the first reaction stage, determine the target pressure adjustment parameter, and control the production pressure according to the target pressure adjustment parameter.

[0042] Furthermore, the data acquisition module 11 is used to perform the following methods: The center position of the bottom of the mold cavity and the center position of the top cover of the mold cavity are taken as the main pressure point set; the edge pressure point set is obtained by identifying the edge pressure point set based on the historical production log set; pressure sensors are deployed at the main pressure point set and the edge pressure point set respectively to obtain the pressure sensor array.

[0043] Furthermore, the data acquisition module 11 is used to perform the following methods: Data retrieval is performed on the historical production log set according to the location of the monitored pressure points and the corresponding pressure change data to obtain a set of monitored pressure point locations and a set of monitored pressure change data. Using the same monitored pressure point location as an index, cluster analysis is performed on the monitored pressure change data sets to determine Q clustered monitored pressure change data sets, where Q is an integer greater than or equal to 1. Based on the Q clustered monitored pressure change data sets, overall fluctuation coefficient analysis is performed to determine Q overall fluctuation coefficients. It is then determined whether the Q overall fluctuation coefficients are greater than or equal to a preset fluctuation coefficient threshold; if so, they are added to the edge pressure point set.

[0044] Furthermore, the data acquisition module 11 is used to perform the following methods: The data change rate is identified by traversing the Q cluster monitoring pressure change data sets to determine Q sets of data change rate sets. The mean of the Q sets of data change rate sets is calculated to obtain Q mean data change rates, and Q mean neighborhoods of the Q mean data change rates are constructed based on a preset neighborhood radius. The Q mean neighborhoods are expanded according to the preset neighborhood radius to obtain Q expanded mean neighborhoods. It is determined whether the neighborhood density of the Q expanded mean neighborhoods is greater than or equal to the neighborhood density of the Q mean neighborhoods. If so, the edges of the Q expanded mean neighborhoods are expanded according to the preset neighborhood radius until a preset stopping condition is met to obtain Q analytical expanded mean neighborhoods. The mean of the data change rate within the Q analytical expanded mean neighborhoods is calculated to obtain the Q overall fluctuation coefficients.

[0045] Furthermore, the data acquisition module 11 is used to perform the following methods: The preset stopping condition is that the number of expansions meets the preset number of expansions or the difference in neighborhood density between two adjacent expansions is less than or equal to the preset neighborhood density difference threshold.

[0046] Furthermore, the identification module 13 is used to perform the following method: The pressure data array sequence, temperature data sequence, and flow data sequence are traversed to identify data change trend features, thereby obtaining pressure data change trend feature array, temperature data change trend features, and flow data change trend features. The pressure data change trend feature array is subjected to interactive fusion analysis to determine the fused pressure data change trend features. Based on the fused pressure data change trend features, temperature data change trend features, and flow data change trend features, reaction stage identification is performed to determine the first reaction stage.

[0047] Furthermore, the identification module 13 is used to perform the following method: Without replacement, randomly extract any two pressure data change trend features from the pressure data change trend feature array and perform feature interaction fusion to determine the first interactive pressure data change trend feature; then, without replacement, randomly extract another pressure data change trend feature and perform feature interaction fusion with the first interactive pressure data change trend feature to obtain the second interactive pressure data change trend feature; after multiple fusions, obtain the fused pressure data change trend feature.

[0048] Furthermore, the identification module 13 is used to perform the following method: Calculate the set of sub-feature similarity coefficients of two pressure data change trend features, and construct a first interaction matrix after normalization. Randomly perform convolution analysis between any one of the two pressure data change trend features and the first interaction matrix to obtain the first interactive pressure data change trend feature.

[0049] Furthermore, the control module 14 is used to perform the following methods: A regulation feedback window is determined, and pressure is continuously monitored within the regulation feedback window to obtain the first regulation feedback result.

[0050] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0051] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0052] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for intelligent control of production pressure in aerated concrete block manufacturing, characterized in that, The method includes: Slurry is injected into the molding die, and at the same time, the pressure sensor array deployed on the inner cavity of the molding die is activated to collect pressure change data and obtain a pressure data array sequence, wherein each pressure data has a corresponding timestamp; The temperature sensor and flow sensor are used in conjunction with timestamps to perform synchronous sensing, and the synchronously mapped temperature data sequence and flow data sequence are obtained. Based on the pressure data array sequence, temperature data sequence, and flow rate data sequence, the reaction stage is identified to determine the first reaction stage; Based on the pressure control target of the first reaction stage, the current real-time pressure control parameters are optimized and adjusted to determine the target pressure adjustment parameters, and the production pressure is controlled according to the target pressure adjustment parameters.

2. The intelligent pressure control method for aerated concrete block production as described in claim 1, characterized in that, Slurry is injected into the molding die, and simultaneously, an array of pressure sensors deployed on the inner cavity of the molding die is activated to collect pressure change data, including: The center position of the bottom of the mold cavity and the center position of the top cover of the mold cavity are taken as the set of main pressure points; Edge pressure points are identified based on historical production log sets to obtain a set of edge pressure points. Pressure sensors are deployed at the main pressure point set and the edge pressure point set respectively to obtain the pressure sensor array.

3. The intelligent pressure control method for aerated concrete block production as described in claim 2, characterized in that, Edge stress point identification is performed based on historical production log sets to obtain a set of edge stress points, including: Data retrieval is performed on the historical production log set according to the location of the monitored pressure points and the corresponding pressure change data to obtain the set of monitored pressure point locations and the set of monitored pressure change data. Using the location of the same monitoring pressure point as an index, cluster analysis is performed on the monitoring pressure change data set to determine Q clustered monitoring pressure change data sets, where Q is an integer greater than or equal to 1; Based on the Q cluster monitoring pressure change data sets, an overall fluctuation coefficient analysis is performed to determine the Q overall fluctuation coefficients; Determine whether the Q overall fluctuation coefficients are greater than or equal to a preset fluctuation coefficient threshold. If so, add them to the edge pressure point set.

4. The intelligent pressure control method for aerated concrete block production as described in claim 3, characterized in that, Based on the aforementioned Q cluster monitoring pressure change data sets, an overall fluctuation coefficient analysis is performed to determine Q overall fluctuation coefficients, including: The data change rate is identified by traversing the Q cluster monitoring pressure change data sets to determine the Q data change rate sets; Calculate the mean of the set of Q data change rates to obtain the mean of Q data change rates, and construct Q mean neighborhoods of the mean of the Q data change rates based on a preset neighborhood radius; The Q mean neighborhoods are expanded according to a preset neighborhood radius to obtain Q expanded mean neighborhoods; Determine whether the neighborhood density of the Q expanded mean neighborhoods is greater than or equal to the neighborhood density of the Q mean neighborhoods. If so, continue to expand the edges of the Q expanded mean neighborhoods according to the preset neighborhood radius until the preset stopping condition is met, and obtain Q analyzed expanded mean neighborhoods. Calculate the mean of the data change rate within the neighborhood of the Q expanded analytical mean to obtain the Q overall fluctuation coefficients.

5. The intelligent pressure control method for aerated concrete block production as described in claim 4, characterized in that, The preset stopping condition is that the number of expansions meets the preset number of expansions or the difference in neighborhood density between two adjacent expansions is less than or equal to the preset neighborhood density difference threshold.

6. The intelligent pressure control method for aerated concrete block production as described in claim 1, characterized in that, Based on the pressure data array sequence, temperature data sequence, and flow rate data sequence, reaction stage identification is performed to determine the first reaction stage, including: The pressure data array sequence, temperature data sequence, and flow data sequence are traversed to identify data change trend features, thereby obtaining pressure data change trend feature array, temperature data change trend feature, and flow data change trend feature; Interactive fusion analysis is performed on the pressure data change trend feature array to determine the fused pressure data change trend features; Based on the characteristics of the fused pressure data, temperature data, and flow data change trends, the reaction stage is identified, and the first reaction stage is determined.

7. The intelligent pressure control method for aerated concrete block production as described in claim 6, characterized in that, Interactive fusion analysis is performed on the pressure data change trend feature array to determine the fused pressure data change trend features, including: Randomly extract any two pressure data change trend features from the pressure data change trend feature array without replacement and perform feature interaction fusion to determine the first interactive pressure data change trend feature. Without replacement, a stress data change trend feature is randomly extracted again and fused with the first interactive stress data change trend feature to obtain the second interactive stress data change trend feature. After multiple fusions, the changing trend characteristics of the fused pressure data are obtained.

8. The intelligent pressure control method for aerated concrete block production as described in claim 7, characterized in that, include: Calculate the set of sub-feature similarity coefficients of the changing trend characteristics of two pressure data, and construct the first interaction matrix after normalization; Randomly perform convolution analysis between any one of the two pressure data change trend features and the first interaction matrix to obtain the first interactive pressure data change trend feature.

9. The intelligent pressure control method for aerated concrete block production as described in claim 1, characterized in that, A regulation feedback window is determined, and pressure is continuously monitored within the regulation feedback window to obtain the first regulation feedback result.

10. An intelligent pressure control system for aerated concrete block production, characterized in that, The system for implementing the intelligent pressure control method for aerated concrete block production according to any one of claims 1-9, the system comprising: The data acquisition module is used to inject slurry into the molding die and simultaneously activate the pressure sensor array deployed on the inner cavity of the molding die to collect pressure change data and obtain a pressure data array sequence, wherein each pressure data has a corresponding timestamp. The sensing module is used to call the temperature sensor and flow sensor to perform synchronous sensing with timestamps, and obtain synchronously mapped temperature data sequence and flow data sequence. The identification module is used to identify the reaction stage based on the pressure data array sequence, temperature data sequence, and flow data sequence, and to determine the first reaction stage; The control module is used to optimize and adjust the current real-time pressure control parameters based on the pressure control target of the first reaction stage, determine the target pressure adjustment parameters, and control the production pressure according to the target pressure adjustment parameters.

Images