Intelligent detection method for strength of aerated brick prepared based on ceramsite fired by building residue soil

Abstract

The invention belongs to the technical field of intelligent manufacturing and quality detection of building materials, and particularly discloses an intelligent strength detection method of an aerated brick prepared based on ceramsite fired by building muck, the method comprises the following steps: detecting key performance parameters of ceramsite, generating initial ingredients and maintenance process parameters through a raw material-process matching rule base, setting a multi-dimensional process signal expected threshold according to historical data, preparing a green body, starting autoclaved curing, collecting process signals in real time, resolving a process parameter adjustment value through a multivariable collaborative algorithm based on signal deviation when the process is abnormal, performing closed-loop real-time regulation and control until curing is finished, recording the regulation and control value, and calculating a process stability coefficient; performing strength sampling detection on the finished product, and comprehensively judging whether the strength quality is qualified or not by combining a process stability coefficient; according to the invention, full-process closed-loop control from raw material adaptation, process dynamic regulation and control to quality intelligent judgment is realized, and the self-adaptive capability and quality stability of aerated brick production are improved.

Description

Technical Field

[0001] This invention belongs to the field of intelligent manufacturing and quality testing technology of building materials, and relates to an intelligent strength testing method for aerated bricks prepared from ceramsite made from construction waste. Background Technology

[0002] With the continuous acceleration of urbanization in my country, the amount of construction waste generated is increasing daily, and its resource utilization has become a major issue in promoting the green development of urban and rural construction. Construction waste, as a major component of construction waste, can be used to produce ceramsite from its main raw material, which is then further used to produce autoclaved aerated concrete (AAC) blocks. This represents a promising high-value-added resource utilization path. This technology not only enables large-scale disposal of solid waste and reduces the consumption of natural resources, but also produces AAC blocks with excellent thermal insulation and heat preservation properties.

[0003] However, the diverse sources and fluctuating composition of construction waste lead to significant differences in the physical properties and chemical activity of the ceramsite produced from it. This variability in raw materials directly impacts the subsequent preparation of aerated bricks, particularly posing a severe challenge to the stability of the autoclaving process. The process parameters such as temperature and pressure during autoclaving, as well as the reaction state within the green body, directly affect the formation of hydration products and the strength of the final product.

[0004] Currently, the industry's quality control of aerated concrete block strength mainly relies on offline, destructive sampling inspection of finished products. This has the following inherent drawbacks: 1. The existing technology can only obtain the quality inspection results of aerated concrete block strength after the entire batch of products has been produced. It cannot identify and intervene in abnormal states during the production process in real time. When the strength is determined to be unqualified, the entire batch of products has already been determined, leading to a comprehensive waste of resources, energy and production costs.

[0005] 2. Existing production processes mostly adopt fixed or experience-based autoclaving systems, lacking dynamic adjustment mechanisms for the performance of specific batches of ceramsite raw materials. This makes it difficult to adaptively adjust to fluctuations in raw material properties, resulting in insensitivity of the production process to changes in raw materials and consequently poor product quality consistency. Summary of the Invention

[0006] In view of this, in order to solve the problems mentioned in the background technology, an intelligent strength detection method for aerated bricks based on ceramsite prepared from construction waste is proposed.

[0007] The objective of this invention can be achieved through the following technical solution: This invention provides an intelligent strength detection method for aerated bricks based on ceramsite prepared from construction waste, including: S1, detecting the key performance parameters of the current batch of ceramsite prepared from construction waste, inputting them into a raw material-process matching rule library constructed based on historical data, and mapping them to generate an initial batching scheme and initial autoclaving process parameters.

[0008] S2. Based on historical data and initial process parameters, determine the expected threshold range of each multi-dimensional process signal, and prepare aerated brick blanks according to the initial batching scheme.

[0009] S3. Start the curing process and collect the measured values ​​of various multi-dimensional process signals in real time to determine whether the process status is abnormal. If the process status is abnormal, the process parameter adjustment value is calculated based on the deviation of each abnormal signal through a multi-variable collaborative control algorithm, and the curing process is adjusted in real time accordingly. This process continues to cycle until the current batch of autoclaving process ends.

[0010] S4. Record the adjustment values ​​of process parameters for each control operation, and calculate the process stability coefficient of the current batch of aerated concrete blocks accordingly.

[0011] S5. Conduct strength sampling tests on the current batch of aerated concrete blocks and, in conjunction with the process stability coefficient, comprehensively determine whether the strength quality of the current batch of aerated concrete blocks is up to standard.

[0012] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention pre-constructs a raw material-process matching rule library based on the compressive strength of ceramsite cylinder and the activity index of pozzolanic ash, and detects the key performance parameters of the current batch of ceramsite before production to match and call the corresponding initial process scheme, thereby providing corresponding initial production guidance for ceramsite raw materials of construction waste with different characteristics, reducing the problem of process incompatibility caused by raw material fluctuations, and improving the accuracy of process setting and the adaptability of raw materials.

[0013] (2) This invention uses real-time acquisition of measured values ​​of multi-dimensional process signals to determine whether the process status is abnormal, transforming traditional result detection into process status monitoring, improving the immediacy of abnormal deviation detection in the maintenance process, providing a clear basis for subsequent intervention, and realizing online perception and diagnosis of the core quality formation process.

[0014] (3) After the process state is determined to be abnormal, the present invention calculates the process parameter adjustment value based on the quantitative deviation of each abnormal signal through a multivariate collaborative control algorithm and performs real-time regulation. The execution process is cycled until the end of the curing, realizing the closed-loop optimization control of the autoclaving dynamics, and continuously stabilizing the process state within the expected range, thereby improving the self-adaptive capability of the production process.

[0015] (4) The present invention records and analyzes the control records in the current batch production, and uses a preset evaluation function to calculate the process stability coefficient. This coefficient objectively quantifies the degree of control and the magnitude of fluctuation in the production process, and provides a quantifiable intermediate evaluation dimension for connecting process performance and final product quality.

[0016] (5) When making the final strength qualification judgment, the present invention introduces the process stability coefficient to generate the dynamic strength judgment threshold, and makes a comprehensive judgment based on the corrected strength data, incorporates process stability into the quality evaluation system, puts forward higher strength requirements for batches with production fluctuations, thereby achieving a more reasonable evaluation of product quality and improving the reliability of quality judgment. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the 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.

[0018] Figure 1 This is a schematic diagram showing the connections between the steps of the method of the present invention.

[0019] Figure 2 This is a schematic diagram illustrating the connection steps of constructing the raw material-process matching rule library of the present invention.

[0020] Figure 3 This is a schematic diagram showing the connection steps of the sampling and testing of the strength of the aerated concrete block product according to the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Please see Figure 1 As shown, the present invention provides an intelligent strength detection method for aerated bricks based on ceramsite made from construction waste. The method includes: S1, detecting the key performance parameters of the current batch of ceramsite made from construction waste, inputting them into a raw material-process matching rule library constructed based on historical data, and mapping them to generate an initial batching scheme and initial autoclaving process parameters.

[0023] Specifically, the raw material-process matching rule library is constructed in the following way: based on the compressive strength and pozzolanic activity index of ceramsite made from construction waste in historical batches, the data distribution characteristics are analyzed, and the compressive strength threshold and pozzolanic activity index threshold for classifying categories are determined. The thresholds are then used to classify multiple ceramsite performance categories in a two-dimensional parameter space composed of the two indicators.

[0024] As an example, the classification of the performance categories of the expanded clay aggregate is achieved through the following steps:

[0025] Collect test data from multiple batches of ceramsite made from construction waste in historical production, including at least the cylinder compressive strength and pozzolanic activity index measured by standard test methods.

[0026] Statistical analysis was performed on the cylinder compressive strength and pozzolanic activity index values ​​in the test data. By analyzing their numerical distribution characteristics, such as using clustering algorithms to find natural grouping boundaries, the grading thresholds for cylinder compressive strength and pozzolanic activity index used to classify raw material categories were determined. For example, based on data density troughs or inflection points in process experience, cylinder compressive strength could be divided into high, medium, and low levels, and activity index into high, medium, and low activity levels.

[0027] A two-dimensional performance coordinate system is constructed with compressive strength as the horizontal axis and pozzolanic activity index as the vertical axis. Using the aforementioned grading thresholds, vertical and horizontal boundary lines are plotted in this coordinate system. These boundary lines divide the entire two-dimensional space into multiple non-overlapping rectangular regions, each defined as a performance category of the ceramsite. Each category can be uniquely described and identified by its corresponding strength and activity range, such as high-strength-high-activity category, medium-strength-medium-activity category, etc.

[0028] The process iterates through all historical production batch data. For each batch whose finished product strength meets the requirements, the ceramsite's compressive strength and pozzolanic activity index are measured and located in the two-dimensional performance space to determine its performance category. Subsequently, the complete batching scheme used in this historically successful batch, such as the type and amount of cementitious materials, water-to-material ratio, admixtures, etc., and the autoclaving process parameters, such as heating rate, constant temperature and time, and pressure, are associated with the ceramsite performance category to obtain multiple ceramsite performance categories.

[0029] For each category of expanded clay aggregate performance, batch data of key performance parameters of expanded clay aggregate falling within the threshold range of the corresponding category and the strength of the prepared aerated bricks are selected from historical production data. In this way, a dataset of batching schemes and autoclaving process parameters corresponding to each category of expanded clay aggregate performance is constructed.

[0030] The datasets corresponding to each performance category of expanded clay aggregate were analyzed to determine the value ranges of key parameters for their batching schemes and the value ranges of key parameters for autoclaving processes.

[0031] Based on the center value of each key parameter range, the batching scheme and autoclaving process parameters corresponding to each ceramsite performance category are determined, and the mapping relationship between each ceramsite performance category and process parameters is established, thus completing the construction of the raw material-process matching rule library.

[0032] Please see Figure 2As shown, exemplarily, the generation of the initial batching scheme and the initial process parameters for autoclaving includes: inputting the key performance parameters into the raw material-process matching rule library for matching, and determining the performance category of the current batch of ceramsite.

[0033] The batching scheme and autoclaving process parameters associated with the performance category of the ceramsite are retrieved respectively to generate an initial batching scheme and initial autoclaving process parameters. If there is a mismatch between the retrieved batching scheme and the autoclaving process parameters, the batching scheme takes priority, and the value range of the autoclaving process parameters is adjusted to ensure compatibility between the two.

[0034] S2. Based on historical data and initial process parameters, determine the expected threshold ranges for each multi-dimensional process signal, and prepare aerated concrete block blanks according to the initial batching scheme. The multi-dimensional process signals include, but are not limited to, the blank's infrared thermal imaging signal and ultrasonic propagation characteristic signal. The blank's infrared thermal imaging signal is acquired using an infrared thermal imager fixedly installed facing the side of the blank, with a sampling frequency of 1 frame / minute. After segmenting the acquired thermal image into regions, the variance of the average temperature of each region is calculated as a characteristic value reflecting the uniformity of temperature distribution. The ultrasonic propagation characteristic signal is acquired using a pair of piezoelectric ultrasonic probes pre-embedded diagonally in the blank, with a transmission frequency of 50kHz. After amplification and filtering, the flight time of the ultrasonic waves through the blank is calculated, and the sound velocity is calculated based on the probe spacing. This sound velocity is used as a characteristic parameter characterizing the internal density of the blank.

[0035] For example, determining the expected threshold range of each multidimensional process signal includes: based on the ceramsite performance category, selecting all historical production batches belonging to that category and whose finished product strength is qualified from historical data, and then obtaining the multidimensional process signal time series data corresponding to each historical production batch.

[0036] For each multidimensional process signal, the signal values ​​of all selected historical batches at each time point are collected to form a signal value sample set at each time point.

[0037] Based on the signal value sample set at each time point, the allowable range of signal fluctuation at each time point is determined by a preset statistical method, thereby generating the expected threshold interval for each multidimensional process signal. The preset statistical method includes, but is not limited to: calculating the mean and standard deviation of the signal value sample set at each time point, and defining the allowable range of signal fluctuation as an interval formed by extending upward and downward by y times the standard deviation, centered on the mean, where y is a positive multiple preset according to the distribution characteristics of historical data and process control requirements, and its typical value range is between 2 and 3.

[0038] The expected threshold ranges for each multidimensional process signal are derived statistically from historical qualified batches under their respective initial process parameters. These ranges represent the typical fluctuation range of each signal when the production process is under control, given the type of ceramsite raw material and the corresponding initial process. Once generated, this range serves as a fixed benchmark for determining whether a significant abnormal deviation has occurred during the current batch's curing process. When an abnormality occurs and adjustments are made, the goal is to bring the process signals back to within this expected threshold range, ensuring that the production process returns to a controllable state confirmed by historical qualified experience.

[0039] S3. The autoclaving process is initiated based on the initial process parameters. Measured values ​​of various multi-dimensional process signals are collected in real time and compared with the corresponding expected threshold ranges to determine if the process status is abnormal. If abnormal, the process parameter adjustment values ​​are calculated using a multi-variable collaborative control algorithm based on the deviations of the abnormal signals. The curing process is then adjusted in real time accordingly. This process continues cyclically until the current batch of autoclaving processes ends. If normal, it indicates that all key parameters of the current autoclaving process are within the controlled expected range. In this case, the current set values ​​of the autoclaving process parameters are maintained unchanged, and the system continues to execute the real-time acquisition and judgment process for the next cycle.

[0040] For example, determining whether the process state is abnormal includes comparing the measured values ​​of each multidimensional process signal with the corresponding expected threshold range.

[0041] The principle is as follows: if the measured values ​​of all multidimensional process signals are within their corresponding expected threshold ranges, it indicates that the current autoclaving process is in a stable and controlled ideal state. Specifically: the temperature and pressure inside the autoclave are maintained within a preset reasonable range, providing a suitable thermodynamic environment for the hydrothermal synthesis reaction of silicon-calcium materials in the billet; the uniformity of the billet's infrared thermographic signal reflects that the spatiotemporal distribution of heat generation inside the billet is normal, with no local overheating or reaction stagnation areas; the normal fluctuation of the ultrasonic propagation characteristic signal means that the internal structure of the billet is uniform, the pore evolution is continuous, and no harmful defects or excessive stress concentrations have formed, at which point the process state is judged to be normal.

[0042] If the measured value of any multidimensional process signal exceeds its corresponding expected threshold range, it indicates that a detectable abnormal deviation has occurred in the production process. Specifically, when the temperature or pressure signal is abnormal, it reflects that the actual working conditions inside the reactor have deviated from the optimal process window, which may directly affect the type and crystallinity of hydration products. When the infrared thermographic signal is abnormal, it suggests that there may be uneven reaction, heat accumulation, or heat transfer obstruction inside the billet, which can easily lead to local performance degradation. When the ultrasonic propagation signal is abnormal, it is usually directly related to newly generated microcracks, pore defects, or uneven density inside the billet, and is a sensitive indicator of the integrity of the internal structure. At this time, the process state is judged to be abnormal.

[0043] Furthermore, the calculation of the process parameter adjustment value includes the following steps: for each abnormal signal, according to its deviation direction, calculate the relative deviation between the measured value and its expected threshold interval boundary value, and use it as the deviation degree of each abnormal signal.

[0044] In one specific embodiment, determining the deviation direction refers to identifying the specific out-of-bounds location of the measured value of the current abnormal signal relative to its expected threshold range. This is achieved by comparing the measured value with the upper and lower limits of the expected threshold range.

[0045] If the measured value is greater than the upper limit of the expected threshold range, the deviation direction of the signal is determined to be positive, that is, the process parameter has exceeded the maximum allowable value, which usually means that the relevant process conditions are too strong, such as too high temperature or too high pressure.

[0046] If the measured value is less than the lower limit of the expected threshold range, the deviation direction of the signal is determined to be negative. This indicates that the process parameters have not reached the required minimum value, which usually means that the relevant process conditions are insufficient, such as too low temperature or incomplete reaction.

[0047] Furthermore, the specific calculation process for the deviation of the abnormal signal includes:

[0048] Based on a clear understanding of the direction of deviation, the relative deviation is calculated using the interval boundary value closest to the measured value of the abnormal signal, i.e., the upper limit of the interval for positive deviation and the lower limit of the interval for negative deviation, as the benchmark.

[0049] When the signal deviates in the positive direction, the difference between the measured value and the upper limit of the expected threshold interval is calculated, and the ratio of the difference to the upper limit of the expected threshold interval is used as the deviation degree.

[0050] When the signal deviates negatively, the difference between the expected lower limit of the threshold interval and the measured value is calculated, and the ratio of the difference to the expected lower limit of the threshold interval is used as the deviation.

[0051] Based on the deviation of all abnormal signals and their preset weights, a weighted fusion calculation is performed to obtain the comprehensive deviation coefficient.

[0052] It should be added that the formula for calculating the comprehensive deviation coefficient is as follows: In the formula This is the comprehensive deviation coefficient. The total number of multidimensional process signals that are currently experiencing anomalies. For the first The deviation of an abnormal signal. For the first Each abnormal signal deviation is assigned a preset weight, and the sum of all weights is 1. .

[0053] Based on this, the weighted fusion calculation of the comprehensive deviation coefficient has the following advantages: on the one hand, by using weight allocation, it can reflect the objective fact that the abnormality of different types of process signals has different degrees of impact on the overall process state, and reflect the difference in importance of different signals in process control; on the other hand, it can directly fuse the deviation information of multiple abnormal signals, and integrate multidimensional and discrete process deviations into a single, quantitative evaluation index, thereby providing an accurate input basis for the subsequent generation of unified process parameter adjustment instructions.

[0054] The preset weights can be pre-set based on the process mechanism and expert experience, or they can be learned from historical production data. For example, collect deviation data for all signal anomalies in historical batches, corresponding process parameter adjustment records, and the final product strength qualification results for that batch; use each signal deviation as the independent variable and the finished product strength qualification as the dependent variable, perform logistic regression analysis to obtain the regression coefficients of each signal deviation; normalize the absolute values ​​of each regression coefficient, and the resulting ratio is the preset weight of each signal deviation.

[0055] Based on the comprehensive deviation coefficient, the adjustment factor for each autoclaving process parameter is calculated, and the initial value of each process parameter is calculated with the corresponding adjustment factor to obtain the adjustment value of each process parameter.

[0056] It should be understood that for each autoclaving process parameter to be adjusted, its adjustment factor needs to be determined according to the following logic:

[0057] The sign of the adjustment factor is determined based on the deviation direction of the abnormal signal that has the strongest physical correlation with the autoclaving process parameters to be controlled. , This is the sequence number of the autoclaving process parameter to be adjusted. For example, if the parameter needs to be increased, take +1; if it needs to be decreased, take -1.

[0058] Using the comprehensive deviation coefficient Based on this, the gain coefficient is adjusted by preset for this parameter. Calculate the amplitude component. Adjustment factor The general formula for calculation is: In the formula, 1 represents maintaining the initial reference. This represents the relative change calculated based on the degree and direction of deviation.

[0059] The pre-setting of the adjustment gain coefficient needs to consider the physical characteristics of each autoclaving process parameter and its sensitivity to product quality. One feasible setting method includes: determining, through process experiments or historical data analysis, the percentage change in the final compressive strength of the aerated concrete block caused by a unit change in each process parameter near its typical operating point, denoted as the sensitivity coefficient. Then, the adjustment gain coefficient is set to be proportional to the reciprocal of the sensitivity coefficient. Based on this principle, if a parameter change is more sensitive to strength, a smaller gain coefficient is assigned to it, ensuring a relatively mild adjustment range for that parameter under the same overall deviation coefficient; conversely, parameters less sensitive to strength are assigned a larger gain coefficient. This method ensures that when process anomalies occur, the adjustment amount of each process parameter is inversely proportional to its influence on the final quality, thereby correcting deviations while avoiding new process oscillations caused by excessive adjustment of a single parameter, achieving synergy in multi-variable adjustments and overall balance of the process system.

[0060] For example, assuming a comprehensive deviation coefficient For the target temperature of the autoclave, if cooling adjustment is required, then Its gain coefficient is 0.1, and its initial value is ℃.

[0061] Calculate adjustment factor , Process parameter adjustment values ℃, meaning the system will automatically update the temperature control target to 171℃.

[0062] S4. Record the adjustment values ​​of process parameters for each control operation, and calculate the process stability coefficient of the current batch of aerated concrete blocks accordingly.

[0063] For example, the calculation of the process stability coefficient of the current batch of aerated concrete blocks includes: counting the total number of anomaly determinations for the current batch and obtaining the maximum absolute value of the process parameter adjustment value.

[0064] Obtain the maximum value of the total number of anomaly determinations and the maximum value of the absolute value of historical adjustment values ​​from historical qualified data, and calculate the relative value of the total number of anomalies and the relative value of the maximum adjustment value for the current batch, respectively.

[0065] Based on the two relative values, the process stability coefficient of the current batch of aerated concrete blocks is calculated using a preset evaluation function.

[0066] It should be noted that the preset evaluation function aims to calculate a process stability coefficient between 0 and 1. The closer the value is to 1, the more stable and controllable the process of that batch is; the closer the value is to 0, the greater the process fluctuation and the more frequent the abnormal intervention.

[0067] In one specific embodiment, the evaluation function is implemented through the following steps to quantify the process stability coefficient: first, the relative value of the total number of anomalies is calculated. , and the relative value of the maximum adjustment value , In the formula, This represents the total number of anomaly detections for the current batch. This represents the maximum total number of anomaly detections among historical qualified data. This represents the maximum absolute value of the process parameter adjustment for the current batch. This represents the maximum absolute value of the process parameter adjustment values ​​in the historical qualified data.

[0068] Next, calculate the initial stability evaluation coefficient. , .

[0069] Finally, the process stability coefficient was obtained through standardization. , .

[0070] S5. Conduct strength sampling tests on the current batch of aerated concrete blocks and, in conjunction with the process stability coefficient, comprehensively determine whether the strength quality of the current batch of aerated concrete blocks is up to standard.

[0071] Please see Figure 3 As shown, exemplarily, the strength sampling test of the current batch of aerated concrete blocks includes: S5-1, dividing the current batch of aerated concrete blocks into several sampling inspection units, and within each sampling inspection unit, according to a preset spatial interval, using a random starting point sampling method, selecting aerated concrete blocks with intact appearance quality as sample blocks.

[0072] For example, sample bricks can be obtained by: based on the total production of the current batch of aerated concrete blocks. According to the preset sampling ratio Calculate the theoretical total number of samples in this batch. In the formula This indicates rounding up to the nearest integer, ensuring that the sample size is an integer and meets the minimum statistical requirements.

[0073] The current batch of aerated concrete blocks is divided into sampling inspection units according to spatial location or production time sequence in the autoclave storage area or packaging line. Number of units: It can be set according to batch size and uniformity requirements, for example when When dividing into blocks, it is divided into 10 units.

[0074] The The sample is evenly distributed among each sampling inspection unit. If the target sample size is allocated to a unit... for: The theoretical total number of samples allocated is calculated as follows: If the value is greater than Then the extra Each sample is subtracted by 1 from each of the first few units to ensure that the actual total number of allocations equals the total number of units allocated. .

[0075] Within each sampling inspection unit, sample bricks of the target sample quantity are drawn according to the following steps: Obtain the total number of aerated concrete bricks in that unit. Calculate the system sampling interval : In the formula This indicates rounding down, and then using a random number generator within the range... Generate an integer to serve as the starting position for this sampling attempt. Starting from the random sampling start position of this unit, every [number] [units] [are generated]. One brick is randomly selected as a candidate sample brick. The appearance quality of the candidate brick is checked: if it is intact, it is included as a sample brick for that unit; if it has appearance defects, the sampling attempt based on that random starting position is deemed invalid, and all candidate bricks already selected based on that starting position are discarded. Subsequently, the random starting position generation step is repeated, i.e., a random number generator is used to generate a random number within the interval... A new integer is generated as the starting position, and the system sampling and appearance judgment are restarted based on this new starting position until a sufficient number of bricks with intact appearance quality are successfully sampled within the sampling inspection unit. To improve sampling efficiency and avoid potential long-term loops under abnormal conditions, a maximum number of attempts W can be set. If W consecutive attempts at random starting positions fail due to appearance quality issues, the sampling strategy is switched: all aerated concrete bricks within the sampling inspection unit are sequentially traversed, and the number of bricks with intact appearance quality up to the target sample size is directly selected as sample bricks. If the number of qualified bricks after traversal is still insufficient to meet the target sample size, the unit is recorded as having insufficient samples.

[0076] S5-2. Cut test specimens of specified geometric shapes and sizes from specific parts of each sample brick, and prepare at least one test specimen for each sample brick.

[0077] S5-3. For all prepared test specimens, mechanical properties were tested under standard conditions according to the compressive strength test method for aerated concrete specified in the industry standard. The failure load of each test specimen was recorded and its compressive strength value was calculated.

[0078] Furthermore, the calculation of the compressive strength value includes: S5-3-1, obtaining the area of ​​the bearing surface of the test specimen based on the specified geometric shape and size.

[0079] S5-3-2. The ratio of the failure load to the area of ​​each test specimen shall be taken as the compressive strength value of each test specimen.

[0080] For example, the comprehensive determination of whether the strength quality of the current batch of aerated concrete blocks is qualified includes: multiplying the process stability coefficient of the current batch with the compressive strength value of all test specimens to obtain the compressive strength correction value of all test specimens.

[0081] The mean and standard deviation of the corrected compressive strength value are calculated to obtain the average compressive strength value and standard deviation.

[0082] The average compressive strength value and standard deviation are compared with their preset dynamic strength judgment threshold and allowable standard deviation threshold, respectively.

[0083] It should be noted that the preset dynamic strength judgment threshold refers to a dynamically changing strength standard value used to determine whether the average compressive strength of a batch is qualified. Its core feature is that this threshold is not fixed, but rather related to the process stability coefficient of the current batch.

[0084] Its specific value is dynamically generated in the following way: First, a benchmark strength qualification value is determined based on the product design strength level. This value is usually specified in national standards or enterprise internal control standards.

[0085] Then, the process stability coefficient of the current batch is introduced. The dynamic threshold is calculated using a preset conversion function. A typical conversion formula is: Dynamic Intensity Determination Threshold. , In the formula To adjust the coefficient, the value range is 0.1-0.3, to ensure that the threshold changes reasonably with the stability coefficient.

[0086] The preset allowable standard deviation threshold refers to the upper limit used to determine whether the strength dispersion of each aerated concrete block specimen within a batch is acceptable. Its specific value is determined by collecting strength data from all test specimens in a large number of historical qualified batches, calculating the standard deviation of strength within each batch, and statistically analyzing these batch standard deviations. For example, the average value plus twice the standard deviation is taken as the allowable standard deviation threshold.

[0087] If the average compressive strength value is greater than or equal to its preset dynamic strength judgment threshold, and the standard deviation is less than or equal to its preset allowable standard deviation threshold, then the strength quality of the current batch of aerated concrete blocks is determined to be qualified; otherwise, the strength quality of the current batch of aerated concrete blocks is determined to be unqualified.

[0088] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0089] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0090] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0091] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0092] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent strength testing of aerated bricks prepared from ceramsite made from construction waste, characterized in that: The method includes: S1. Detect the key performance parameters of the current batch of construction waste ceramsite, input them into the raw material-process matching rule library built based on historical data, and map them to generate the initial batching scheme and the initial process parameters of autoclaving. S2. Based on historical data and initial process parameters, determine the expected threshold range of each multi-dimensional process signal, and prepare aerated brick blanks according to the initial batching scheme; S3. Start the curing process and collect the measured values ​​of various multi-dimensional process signals in real time to determine whether the process status is abnormal. If abnormal, the process parameter adjustment value is calculated based on the deviation of each abnormal signal through a multi-variable collaborative control algorithm, and the curing process is adjusted in real time accordingly. This process continues to cycle until the current batch of autoclaving process ends. S4. Record the adjustment values ​​of process parameters for each control, and calculate the process stability coefficient of the current batch of aerated concrete blocks accordingly. S5. Conduct strength sampling tests on the current batch of aerated concrete blocks and, in conjunction with the process stability coefficient, comprehensively determine whether the strength quality of the current batch of aerated concrete blocks is up to standard.

2. The intelligent strength detection method for aerated bricks based on ceramsite prepared from construction waste as described in claim 1, characterized in that: The construction of the raw material-process matching rule base includes: Based on the compressive strength and pozzolanic activity index of ceramsite made from construction waste in historical batches, the data distribution characteristics were analyzed to determine the compressive strength threshold and pozzolanic activity index threshold for classifying the categories. Using the thresholds, multiple ceramsite performance categories were divided in a two-dimensional parameter space composed of the two indicators. For each category of ceramsite performance, batch data of key performance parameters of ceramsite falling within the threshold range of the corresponding category and the strength of the prepared aerated bricks are selected from historical production data. In this way, a dataset of batching schemes and autoclaving process parameters corresponding to each category of ceramsite performance is constructed. The datasets corresponding to each performance category of expanded clay aggregate were analyzed to determine the value ranges of key parameters for their batching schemes and the value ranges of key parameters for autoclaving processes. Based on the center value of each key parameter range, the batching scheme and autoclaving process parameters corresponding to each ceramsite performance category are determined, and the mapping relationship between each ceramsite performance category and process parameters is established, thus completing the construction of the raw material-process matching rule library.

3. The intelligent strength detection method for aerated bricks based on ceramsite prepared from construction waste as described in claim 2, characterized in that: The initial ingredient ratio and initial autoclaving process parameters include: The key performance parameters are input into the raw material-process matching rule library for matching to determine the performance category of the current batch of ceramsite. The batching scheme and autoclaving process parameters associated with the performance category of the ceramsite are retrieved respectively to generate the initial batching scheme and the initial autoclaving process parameters.

4. The intelligent strength detection method for aerated bricks based on ceramsite prepared from construction waste as described in claim 2, characterized in that: The determination of the expected threshold range for each multidimensional process signal includes: Based on the aforementioned ceramsite performance category, all historical production batches belonging to that category and whose finished product strength is qualified are selected from historical data, thereby obtaining multi-dimensional process signal time series data corresponding to each historical production batch. For each multidimensional process signal, the signal values ​​of all selected historical batches at each time point are collected to form a sample set of signal values ​​at each time point. Based on the signal value sample set at each time point, the allowable range of signal fluctuation at each time point is determined by a preset statistical method, thereby generating the expected threshold range of each multidimensional process signal.

5. The intelligent strength detection method for aerated bricks based on ceramsite prepared from construction waste as described in claim 1, characterized in that: Whether the determination process status is abnormal includes: The measured values ​​of each multidimensional process signal are compared with the corresponding expected threshold ranges; If the measured values ​​of all multidimensional process signals are within their corresponding expected threshold ranges, the process state is considered normal. If the measured value of any multidimensional process signal exceeds its corresponding expected threshold range, the process state is determined to be abnormal.

6. The intelligent strength detection method for aerated bricks based on ceramsite prepared from construction waste as described in claim 1, characterized in that: The adjustment values ​​for the calculation process parameters include: For each abnormal signal, the relative deviation between the measured value and the expected threshold interval boundary value is calculated according to its deviation direction, and this deviation is used as the degree of deviation of each abnormal signal. Based on the deviation of all abnormal signals and their preset weights, a weighted fusion calculation is performed to obtain the comprehensive deviation coefficient; Based on the comprehensive deviation coefficient, the adjustment factor for each autoclaving process parameter is calculated, and the initial value of each process parameter is calculated with the corresponding adjustment factor to obtain the adjustment value of each process parameter.

7. The intelligent strength detection method for aerated bricks based on ceramsite prepared from construction waste as described in claim 1, characterized in that: The calculation of the process stability coefficient of the current batch of aerated concrete blocks includes: Count the total number of anomaly detections for the current batch and obtain the maximum absolute value of the process parameter adjustment value; Obtain the maximum value of the total number of anomaly determinations and the maximum value of the absolute value of historical adjustment values ​​from historical qualified data, and calculate the relative value of the total number of anomalies and the relative value of the maximum adjustment value for the current batch, respectively. Based on the two relative values, the process stability coefficient of the current batch of aerated concrete blocks is calculated using a preset evaluation function.

8. The intelligent strength detection method for aerated bricks based on ceramsite prepared from construction waste as described in claim 1, characterized in that: The strength sampling test of the current batch of aerated concrete blocks includes: The current batch of aerated concrete blocks is divided into several sampling inspection units. Within each sampling inspection unit, according to the preset spatial interval, a random starting point sampling method is used to select aerated concrete block finished products with intact appearance quality as sample blocks. Test specimens of specified geometric shapes and sizes are cut from specific parts of each sample brick, and at least one test specimen is prepared for each sample brick. For all prepared test specimens, mechanical properties were tested under standard conditions according to the compressive strength test method for aerated concrete specified in industry standards. The failure load of each test specimen was recorded and its compressive strength value was calculated.

9. The intelligent strength detection method for aerated bricks based on ceramsite prepared from construction waste as described in claim 8, characterized in that: The calculation of the compressive strength value includes: Based on the test specimen with specified geometry and dimensions, obtain the area of ​​the bearing surface of the test specimen; The ratio of the failure load to the area of ​​each test specimen is taken as the compressive strength value of each test specimen.

10. The intelligent strength detection method for aerated bricks based on ceramsite prepared from construction waste as described in claim 1, characterized in that: The comprehensive determination of whether the strength and quality of the current batch of aerated concrete blocks are up to standard includes: The compressive strength correction value for all test specimens is obtained by multiplying the process stability coefficient of the current batch with the compressive strength value of all test specimens respectively. The mean and standard deviation of the corrected compressive strength value are calculated to obtain the average compressive strength value and standard deviation. The average compressive strength value and standard deviation are compared with their preset dynamic strength judgment threshold and allowable standard deviation threshold, respectively; If the average compressive strength value is greater than or equal to its preset dynamic strength judgment threshold, and the standard deviation is less than or equal to its preset allowable standard deviation threshold, then the strength quality of the current batch of aerated concrete blocks is judged to be qualified; otherwise, the strength quality of the current batch of aerated concrete blocks is judged to be unqualified.

Images