Concrete proportioning automatic checking method, device and equipment and storage medium

Abstract

The application belongs to the technical field of concrete, and discloses a concrete proportioning automatic checking method, device, equipment and storage medium. The method comprises the following steps: collecting original proportioning parameters of to-be-checked concrete proportioning, and collecting real-time field dynamic interference parameters through a sensor; performing field performance testing on actual concrete mixture to obtain measured working performance data and initial strength data; performing compressive strength simulation on the original proportioning parameters and the field dynamic interference parameters through a strength prediction model to obtain theoretical strength data; comparing the measured working performance data, the initial strength data and the theoretical strength data to obtain a strength checking result; calling corresponding checking rules from a preset checking rule library based on the field dynamic interference parameters; and performing automatic checking based on the strength checking result, the checking rules and the original proportioning parameters. In the above manner, static artificial judgment is converted into dynamic intelligent verification, and the checking efficiency and accuracy are improved.

Description

Technical Field

[0001] This invention relates to the field of concrete testing technology, and in particular to an automatic verification method, apparatus, equipment and storage medium for concrete mix proportions. Background Technology

[0002] Concrete mix design is a core technical parameter that determines the strength, workability, durability, and economy of concrete. Its accuracy directly affects the safety of the engineering structure and the construction cost. Currently, the verification of concrete mix design mainly relies on traditional manual experience and static standards and specifications. For example, designers initially propose a mix design based on engineering requirements, conduct laboratory trials to test properties such as slump and compressive strength, and then make manual judgments to determine whether it meets the standards. The above method leads to a disconnect between static rules and dynamic working conditions, low efficiency of manual intervention, and low accuracy.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide an automatic concrete mix design verification method, apparatus, equipment, and storage medium, aiming to solve the technical problems of current methods, such as the disconnect between static rules and dynamic working conditions, low efficiency of manual intervention, and low accuracy.

[0005] To achieve the above objectives, the present invention provides an automatic concrete mix design verification method, which includes the following steps: The original mix proportion parameters of the concrete mix proportion to be checked are collected, and the dynamic interference parameters on site are collected in real time through sensors. The dynamic interference parameters include the real-time performance parameters of raw materials and the real-time parameters of construction conditions. On-site performance tests were conducted on actual concrete mixtures to obtain measured work performance data and initial strength data. The compressive strength was simulated using a strength prediction model based on the original mix proportions and the on-site dynamic environmental parameters to obtain theoretical strength data. The measured working performance data and the initial strength data are compared with the theoretical strength data to obtain the strength verification results; Based on the on-site dynamic interference parameters, the corresponding verification rules are called from the preset verification rule library. The verification rules include environmental adaptability intensity threshold, working condition matching performance range, material usage limit and durability index. Automatic verification is performed based on the strength verification results, the verification rules, and the original proportioning parameters.

[0006] In some embodiments, the on-site performance testing of the actual concrete mixture to obtain measured workability data and initial strength data includes: The test items are determined based on the set project type. The test items include at least the slump, spread, initial setting time, and initial strength of structural concrete, and the additional pressure bleeding rate of pumped concrete. A slump test was conducted on the actual concrete mixture to obtain a reference slump. Obtain the current ambient temperature during the field performance test; If the current ambient temperature does not meet the preset conditions, the reference slump is corrected to obtain a corrected slump. The corrected slump is used as measured performance data, and the correction formula is as follows: S 修正 =S 参考 ×[1+0.01×(20-T)]; Among them, S 修正 S represents the corrected slump. 参考 The reference slump is represented by T, and the current ambient temperature is represented by T. The compressive strength was tested using a pressure testing machine to obtain the initial strength data.

[0007] In some embodiments, the method further includes: Collect historical engineering datasets and use these datasets as features as input; The correlation coefficient of the input features is determined by the Pearson correlation coefficient, and the input features with correlation coefficients greater than the preset coefficient are retained to obtain the target engineering dataset; The target engineering dataset is divided into a training set and a validation set. An LSTM deep learning model is selected and the Adam optimizer is used. The initial learning rate is 0.001, which decays by 10% every 50 rounds. The loss function is the mean squared error (MSE). The network structure includes an input layer, a hidden layer, and an output layer. The model is trained using the training set and its performance is evaluated using the validation set. Training stops when the mean absolute error is less than a preset error, thus obtaining the intensity prediction model.

[0008] In some embodiments, the step of calling the corresponding verification rule from the preset verification rule base based on the on-site dynamic interference parameters includes: The on-site dynamic interference parameters are preprocessed, and the real-time performance parameters of raw materials included in the preprocessed on-site dynamic interference parameters are classified. The corresponding rule set is located by matching the parameter range in the preset verification rule base with the real-time performance parameters of the classified raw materials. The rule set is threshold-corrected based on the construction conditions included in the on-site dynamic interference parameters; Invoke the verification rules from the revised rule set.

[0009] In some embodiments, adjusting the rule set according to the construction conditions included in the on-site dynamic interference parameters includes: The influence weight values ​​of the on-site dynamic disturbance parameters are determined by the analytic hierarchy process (AHP). These influence weight values ​​include the weight of sand and gravel moisture content, the weight of ambient temperature, the weight of transportation distance, the weight of cement temperature, and the weight of aggregate gradation fluctuation. Calculate the comprehensive interference coefficient based on the aforementioned influence weight values; The correction intensity level is determined based on the comprehensive interference coefficient; Based on the correction intensity level and the influence weight value, several parameters with the largest influence weight are selected, and the threshold of each verification rule in the rule set is corrected based on the several parameters with the largest influence weight.

[0010] In some embodiments, the automatic verification based on the strength verification result, the verification rules, and the original proportioning parameters includes: The environmental adaptability strength threshold, cement dosage limit, and durability index threshold are determined according to the aforementioned verification rules. The strength deviation rate is determined based on the environmental adaptability strength threshold and the strength verification results to complete the strength verification; The amount of cement in the original proportioning parameters is compared with the cement content limit to complete the material content verification; The durability index value is calculated based on the original proportioning parameters, and the durability index value is compared with the durability index threshold to complete the durability verification.

[0011] In some embodiments, the method further includes: Calculate the sensitivity coefficient corresponding to each parameter in the original proportioning parameters; The parameter adjustment priority is determined based on the sensitivity coefficient; The parameter adjustment amount is determined based on the automatic verification results; The original proportioning parameters are adjusted according to the parameter adjustment priority and the parameter adjustment amount.

[0012] Furthermore, to achieve the above objectives, the present invention also proposes an automatic concrete mix design verification device, the automatic concrete mix design verification device comprising: The data acquisition module is used to acquire the original mix proportion parameters of the concrete mix proportion to be checked, and to acquire the dynamic interference parameters on site in real time through sensors. The dynamic interference parameters include the real-time performance parameters of raw materials and the real-time parameters of construction conditions. The testing module is used to conduct on-site performance tests on actual concrete mixtures to obtain measured work performance data and initial strength data. The simulation module is used to perform compressive strength simulation on the original mix proportion parameters and the on-site dynamic environmental parameters through a strength prediction model to obtain theoretical strength data; The verification module is used to compare the measured working performance data and the initial strength data with the theoretical strength data to obtain the strength verification result; The calling module is used to call the corresponding verification rules from the preset verification rule library based on the on-site dynamic interference parameters. The verification rules include environmental adaptability intensity threshold, working condition matching performance range, material usage limit and durability index. The verification module is used to perform automatic verification based on the strength verification results, the verification rules, and the original proportioning parameters.

[0013] Furthermore, to achieve the above objectives, the present invention also proposes an automatic concrete mix design verification device, which includes: a memory, a processor, and an automatic concrete mix design verification program stored in the memory and executable on the processor. The automatic concrete mix design verification program is configured to implement the steps of the automatic concrete mix design verification method described above.

[0014] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing an automatic concrete mix design program, wherein the automatic concrete mix design program, when executed by a processor, implements the steps of the automatic concrete mix design method described above.

[0015] This invention collects the original mix proportion parameters of the concrete mix to be verified and uses sensors to collect dynamic interference parameters in real time. On-site performance tests are conducted on the actual concrete mixture to obtain measured working performance data and initial strength data. A strength prediction model is used to simulate the compressive strength of the original mix proportion parameters and on-site dynamic environmental parameters to obtain theoretical strength data. The measured working performance data and initial strength data are compared with the theoretical strength data to obtain the strength verification result. Based on the on-site dynamic interference parameters, corresponding verification rules are called from a preset verification rule library. Automatic verification is performed based on the strength verification result, the verification rules, and the original mix proportion parameters. Through this method, static manual judgment is transformed into dynamic intelligent verification, improving verification efficiency and accuracy. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the first embodiment of the automatic concrete mix design verification method of the present invention. Figure 2This is a structural block diagram of the first embodiment of the automatic concrete mix proportion verification device of the present invention.

[0017] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0019] This invention provides an automatic concrete mix design verification method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the automatic concrete mix design verification method of the present invention.

[0020] In this embodiment, the automatic concrete mix design verification method includes the following steps: Step S10: Collect the original mix proportion parameters of the concrete mix proportion to be checked, and collect the dynamic interference parameters on site in real time through sensors.

[0021] In this embodiment, the executing entity is an automatic concrete mix design verification device. This device has functions such as data processing, data communication, and program execution. The device can be a computer terminal or other network device, or other devices with similar functions. This embodiment does not limit the scope of the device.

[0022] In this specific implementation, the original mix proportion parameters of the concrete mix to be checked are first collected, and at the same time, dynamic interference parameters on site are collected in real time through sensors. The original mix proportion parameters include cementitious material dosage, water-cement ratio, aggregate gradation, admixture dosage, etc. The dynamic interference parameters include real-time performance parameters of raw materials and real-time parameters of construction conditions. Real-time performance parameters of raw materials include sand and gravel moisture content, cement temperature, gradation fluctuation value, etc. Construction conditions include ambient temperature, transportation distance of transport vehicles, mixing time, etc.

[0023] Furthermore, this embodiment can filter outliers in the collected data, for example, removing outliers where the moisture content of sand and gravel is greater than 10%. By realizing real-time perception of raw material properties and construction conditions, a data foundation is provided for dynamic verification, avoiding verification deviations caused by parameter lag.

[0024] Step S20: Conduct on-site performance tests on the actual concrete mixture to obtain measured work performance data and initial strength data.

[0025] In this specific implementation, the actual concrete mixture is first subjected to on-site performance testing to obtain measured workability data and initial strength data. The specific process involves determining test items based on the defined project type. These test items include at least the slump, spread, initial setting time, and initial strength of structural concrete, and the additional pressure bleeding rate for pumped concrete. A slump test is performed on the actual concrete mixture to obtain a reference slump. The current ambient temperature during the on-site performance test is then obtained. If the current ambient temperature does not meet preset conditions, the reference slump is corrected to obtain a corrected slump. This corrected slump is used as the measured workability data, and a compressive strength test is conducted using a pressure testing machine to obtain initial strength data.

[0026] It should be noted that, for example, the slump test involves filling the actual concrete mixture into a slump cone in three layers, tamping each layer 25 times, and then measuring the slump height after lifting the cone to obtain the reference slump.

[0027] Furthermore, the correction formula corresponding to the above correction process is: S 修正 =S 参考 ×[1+0.01×(20-T)]; Among them, S 修正 S represents the corrected slump. 参考 The value represents the reference slump, and T represents the current ambient temperature.

[0028] In this embodiment, the loading rate of the electro-hydraulic servo pressure testing machine can be set to 0.6 MPa / s. When performing compressive strength testing, the average value of multiple compressive strength results is taken as the initial strength data. For example, assuming the compressive strength results are 28.5 MPa, 29.2 MPa, and 28.8 MPa, the average value of 28.8 MPa is taken as the initial strength data.

[0029] Step S30: Perform compressive strength simulation on the original mix proportion parameters and the on-site dynamic environmental parameters using a strength prediction model to obtain theoretical strength data.

[0030] In this specific implementation, an intensity prediction model needs to be constructed first. Specifically, a historical engineering dataset is collected and used as input features. The correlation coefficient of the input features is determined by the Pearson correlation coefficient, and input features with correlation coefficients greater than a preset coefficient are retained to obtain the target engineering dataset. The target engineering dataset is divided into a training set and a validation set. An LSTM deep learning model is selected and the Adam optimizer is used. The initial learning rate is 0.001, which decays by 10% every 50 rounds. The loss function is the mean squared error (MSE). The network structure includes an input layer, a hidden layer, and an output layer. The model is trained using the training set and its performance is evaluated using the validation set. Training stops when the mean absolute error is less than a preset error to obtain the intensity prediction model.

[0031] It should be noted that historical engineering data includes parameters such as concrete mix proportions (cement dosage, water-cement ratio, mineral admixture ratio, sand ratio), raw material performance parameters (cement grade, sand and gravel moisture content, type and dosage of admixtures), construction environment parameters (curing temperature, curing humidity), and measured compressive strength values. The Pearson correlation coefficient formula is used to calculate the correlation coefficient.

[0032] Where x represents the input parameters (such as cement dosage, water-cement ratio, mineral admixture ratio, sand ratio, cement grade, sand and gravel moisture content ω, admixture type and dosage, etc.), n represents the total number of parameters, and y represents the measured compressive strength value. The preset coefficient can be set to 0.6, meaning that input features with a correlation coefficient greater than 0.6 are retained to obtain the target engineering dataset. The preset error can be set to 2MPa, meaning that training stops when the mean absolute error is <2MPa; otherwise, the number of neurons in the hidden layer is increased or an attention mechanism is introduced for optimization. Finally, the model weights and parameter files are saved.

[0033] Furthermore, this strength prediction model can be used to simulate compressive strength by combining the original mix proportions and on-site dynamic environmental parameters, thereby obtaining theoretical strength data. For example, by inputting the original mix proportions and on-site environmental parameters into the strength prediction model, the theoretical output compressive strength data is f=52.3MPa, that is, the theoretical strength data is 52.3MPa.

[0034] Step S40: Compare the measured working performance data and the initial strength data with the theoretical strength data to obtain the strength verification result.

[0035] In practice, the actual strength contained in the measured working performance data is compared with the theoretical strength data to obtain the strength verification result, which is the strength deviation rate. The calculation formula is δ=C1-C2 / C2, where δ represents the strength deviation rate, and C1 and C2 represent the actual strength and theoretical strength data contained in the measured working performance data, respectively. For example, the initial strength data is 28.8 MPa. Due to the variation in strength caused by different numbers of days, the actual strength data corresponding to the initial strength data is 50.5 MPa, while the theoretical strength data obtained from the strength prediction model is 52.3 MPa, resulting in a strength deviation rate of 3.4%.

[0036] Step S50: Based on the on-site dynamic interference parameters, call the corresponding verification rules from the preset verification rule library.

[0037] It should be noted that the verification rules in this embodiment are dynamic and are based on on-site dynamic interference parameters. The verification rules include environmental adaptability intensity threshold, working condition matching performance range, material usage limit and durability index.

[0038] In the specific implementation, the on-site dynamic interference parameters are preprocessed, and the real-time performance parameters of raw materials included in the preprocessed on-site dynamic interference parameters are classified; the parameter range in the preset verification rule base is matched according to the classified real-time performance parameters of raw materials to locate the corresponding rule set; the rule set is threshold-corrected according to the construction conditions included in the on-site dynamic interference parameters; and the verification rules in the corrected rule set are called.

[0039] It should be noted that the preset verification rule base contains verification rules with different parameters, and there are corresponding parameter ranges. For example, the parameters corresponding to the moisture content of sand and gravel are [0%, 3%], [3%, 7%], and (7%, 10%). The above three parameter ranges correspond to the low moisture content rule group, the medium moisture content rule group, and the high moisture content rule group, respectively. Another example is the ambient temperature T. a Including T a ≤5℃, 5℃<T a ≤30℃ and T a For the three parameter ranges >30℃, corresponding to low-temperature, normal-temperature, and high-temperature rules, a corresponding parameter range and verification rule can be obtained for each parameter, thus forming a rule set. Each rule in the rule set has its corresponding threshold. In this embodiment, adjustments can be made based on construction conditions to make the verification rules in the modified rule set more consistent with the site environment. The verification rule invoked is the verification rule in the modified rule set.

[0040] Furthermore, the adjustment process specifically involves using the analytic hierarchy process (AHP) to determine the influence weight values ​​of the on-site dynamic interference parameters. These influence weight values ​​include the weights of sand and gravel moisture content, ambient temperature, transportation distance, cement temperature, and aggregate gradation fluctuation. A comprehensive interference coefficient is calculated based on these influence weight values. A correction intensity level is determined based on the comprehensive interference coefficient. Based on the correction intensity level and the influence weight values, several parameters with the largest influence weights are selected, and the threshold values ​​of each verification rule in the rule set are corrected based on these parameters with the largest influence weights.

[0041] It should be noted that, for example, the influence weight values ​​of on-site dynamic interference parameters are as follows: ambient temperature 0.25, sand and gravel moisture content 0.3, transportation distance 0.2, cement temperature weight and aggregate gradation fluctuation value weights are 0.15 and 0.1 respectively. The comprehensive interference coefficient K = 0.25×0.6 + 0.3×0.3 + 0.2×0.6 + 0.15×0.3 + 0.1×0.3 = 0.435. Based on the K value, the correction intensity level is divided: K ≤ 0.3 is light correction, 0.3 < K ≤ 0.6 is moderate correction, and K > 0.6 is severe correction. The number of parameters to be screened is determined based on this correction intensity level; for example, light correction corresponds to 3 parameters, moderate correction corresponds to 4 parameters. Then, the parameters with the highest influence weights are selected. The four parameters for moderate correction are ambient temperature, sand and gravel moisture content, transportation distance, and cement temperature. Finally, for example, taking the moisture content of sand and gravel, if it is a low moisture content rule, the lower limit is lowered; if it is a medium moisture content rule, the lower limit remains unchanged; if it is a high moisture content rule, the lower limit is raised. The upper and lower limits can be referred to the parameter ranges corresponding to the low moisture content rule, medium moisture content rule group, and high moisture content rule group mentioned above.

[0042] Step S60: Perform automatic verification based on the strength verification result, the verification rules, and the original proportioning parameters.

[0043] In this specific implementation, automatic verification is performed on key or critical parameters. The automatic verification process involves determining the environmental adaptability strength threshold, cement dosage limit, and durability index threshold according to the verification rules; determining the strength deviation rate based on the environmental adaptability strength threshold and strength verification results to complete the strength verification; comparing the cement dosage in the original mix proportion parameters with the cement dosage limit to complete the material dosage verification; calculating the durability index value based on the original mix proportion parameters, and comparing the durability index value with the durability index threshold to complete the durability verification. For example, in strength verification, if the strength deviation rate is ≥-5%, the strength is considered to meet the standard; if -10% ≤ strength deviation rate <-5%, the strength is considered to be slightly substandard; if the strength deviation rate is <-10%, the strength is considered to be seriously substandard. For example, in material dosage verification, if m1 ≤ m 1maxTo determine if the material usage is compliant, if m1 > m 1max The material usage was determined to be excessive, m1 and m 1max These represent the cement content and cement content limit in the original mix design parameters, respectively. For durability verification, for example, Da = 10⁻¹² × exp(0.1 × m₁ - 0.05 × λ), where m₁ is the cement content and λ is the proportion of mineral admixtures. If D… a ≤1.0×10 -12 m 2 If the value is / s, the durability is deemed to meet the standard; otherwise, the durability is deemed to fail to meet the standard.

[0044] Furthermore, based on the verification results, the parameters can be further adjusted in this embodiment. The specific process is as follows: calculate the sensitivity coefficient corresponding to each parameter in the original proportion parameters; determine the parameter adjustment priority based on the sensitivity coefficient; determine the parameter adjustment amount based on the automatic verification results; and adjust the original proportion parameters according to the parameter adjustment priority and the parameter adjustment amount.

[0045] It should be noted that the sensitivity coefficient is ,in, and For verification The determined intensity change and the actual strength, and The sensitivity coefficient determines the priority of parameter adjustments based on the change in the original mix proportion parameters. For example, the priority order is: admixture dosage (Km=1.8) > sand ratio (Km=1.2) > water content (Km=0.9). The parameter adjustment amount can be, for example, the difference between the cement content and the cement content limit in material usage verification. Finally, adjustments are made according to the determined priority.

[0046] In this embodiment, the original mix proportion parameters of the concrete mix to be verified are collected, and the dynamic interference parameters on site are collected in real time by sensors. On-site performance tests are conducted on the actual concrete mixture to obtain measured working performance data and initial strength data. The compressive strength is simulated using a strength prediction model based on the original mix proportion parameters and on-site dynamic environmental parameters to obtain theoretical strength data. The measured working performance data and initial strength data are compared with the theoretical strength data to obtain the strength verification result. The corresponding verification rules are called from the preset verification rule library based on the on-site dynamic interference parameters. Automatic verification is performed based on the strength verification result, verification rules, and original mix proportion parameters. Through the above method, static manual judgment is transformed into dynamic intelligent verification, improving the verification efficiency and accuracy.

[0047] Furthermore, this embodiment of the invention also proposes a storage medium storing an automatic concrete mix design verification program, which, when executed by a processor, implements the steps of the automatic concrete mix design verification method described above.

[0048] Reference Figure 2 , Figure 2 This is a structural block diagram of the first embodiment of the automatic concrete mix proportion verification device of the present invention.

[0049] like Figure 2 As shown, the automatic concrete mix design verification device proposed in this embodiment of the invention includes: The acquisition module 10 is used to acquire the original mix proportion parameters of the concrete mix proportion to be checked, and to acquire the dynamic interference parameters on site in real time through sensors. The dynamic interference parameters include the real-time performance parameters of raw materials and the real-time parameters of construction conditions. Test module 20 is used to conduct on-site performance tests on actual concrete mixtures to obtain measured working performance data and initial strength data; Simulation module 30 is used to perform compressive strength simulation on the original mix proportion parameters and the on-site dynamic environmental parameters through a strength prediction model to obtain theoretical strength data; Verification module 40 is used to compare the measured working performance data and the initial strength data with the theoretical strength data to obtain the strength verification result; The calling module 50 is used to call the corresponding verification rules from the preset verification rule library based on the on-site dynamic interference parameters. The verification rules include environmental adaptability intensity threshold, working condition matching performance range, material usage limit and durability index. The verification module 60 is used to perform automatic verification based on the strength verification results, the verification rules, and the original proportioning parameters.

[0050] In this embodiment, the original mix proportion parameters of the concrete mix to be verified are collected, and dynamic interference parameters on site are collected in real time through sensors. On-site performance tests are conducted on the actual concrete mixture to obtain measured working performance data and initial strength data. A strength prediction model is used to simulate the compressive strength of the original mix proportion parameters and on-site dynamic environmental parameters to obtain theoretical strength data. The measured working performance data and initial strength data are compared with the theoretical strength data to obtain the strength verification result. Based on the on-site dynamic interference parameters, the corresponding verification rules are called from a preset verification rule base. Automatic verification is performed based on the strength verification result, the verification rules, and the original mix proportion parameters. Through this method, static manual judgment is transformed into dynamic intelligent verification, improving verification efficiency and accuracy. In some embodiments, the test module 20 is used to determine test items based on a set project type. The test items include at least the slump, spread, initial setting time, and initial strength of structural concrete, and the additional pressure bleeding rate of pumped concrete. A slump test was conducted on the actual concrete mixture to obtain a reference slump. Obtain the current ambient temperature during the field performance test; If the current ambient temperature does not meet the preset conditions, the reference slump is corrected to obtain a corrected slump. The corrected slump is used as measured performance data, and the correction formula is as follows: S 修正 =S 参考 ×[1+0.01×(20-T)]; Among them, S 修正 S represents the corrected slump. 参考 The reference slump is represented by T, and the current ambient temperature is represented by T. The compressive strength was tested using a pressure testing machine to obtain the initial strength data.

[0051] In some embodiments, the automatic concrete mix design verification device further includes a construction module; The construction module is used to collect historical engineering datasets and use the historical engineering datasets as features as input. The correlation coefficient of the input features is determined by the Pearson correlation coefficient, and the input features with correlation coefficients greater than the preset coefficient are retained to obtain the target engineering dataset; The target engineering dataset is divided into a training set and a validation set. An LSTM deep learning model is selected and the Adam optimizer is used. The initial learning rate is 0.001, which decays by 10% every 50 rounds. The loss function is the mean squared error (MSE). The network structure includes an input layer, a hidden layer, and an output layer. The model is trained using the training set and its performance is evaluated using the validation set. Training stops when the mean absolute error is less than a preset error, thus obtaining the intensity prediction model.

[0052] In some embodiments, the calling module 50 is used to preprocess the on-site dynamic interference parameters and classify the real-time performance parameters of raw materials included in the preprocessed on-site dynamic interference parameters. The corresponding rule set is located by matching the parameter range in the preset verification rule base with the real-time performance parameters of the classified raw materials. The rule set is threshold-corrected based on the construction conditions included in the on-site dynamic interference parameters; Invoke the verification rules from the revised rule set.

[0053] In some embodiments, the calling module 50 is used to determine the influence weight values ​​of the on-site dynamic interference parameters using the analytic hierarchy process. The influence weight values ​​include the weight of sand and gravel moisture content, the weight of ambient temperature, the weight of transportation distance, the weight of cement temperature, and the weight of aggregate gradation fluctuation value. Calculate the comprehensive interference coefficient based on the aforementioned influence weight values; The correction intensity level is determined based on the comprehensive interference coefficient; Based on the correction intensity level and the influence weight value, several parameters with the largest influence weight are selected, and the threshold of each verification rule in the rule set is corrected based on the several parameters with the largest influence weight.

[0054] In some embodiments, the verification module 60 is used to determine the environmental adaptability strength threshold, cement dosage limit, and durability index threshold according to the verification rules. The strength deviation rate is determined based on the environmental adaptability strength threshold and the strength verification results to complete the strength verification; The amount of cement in the original proportioning parameters is compared with the cement content limit to complete the material content verification; The durability index value is calculated based on the original proportioning parameters, and the durability index value is compared with the durability index threshold to complete the durability verification.

[0055] In some embodiments, the automatic concrete mix design verification device further includes an adjustment module; The adjustment module is used to calculate the sensitivity coefficient corresponding to each parameter in the original proportion parameters; The parameter adjustment priority is determined based on the sensitivity coefficient; The parameter adjustment amount is determined based on the automatic verification results; The original proportioning parameters are adjusted according to the parameter adjustment priority and the parameter adjustment amount.

[0056] This application embodiment also provides an automatic concrete mix design verification device, including a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other through the communication bus. The memory is used to store the automatic concrete mix design verification program. When the processor executes the program stored in the memory, it implements the above-mentioned automatic concrete mix design verification method.

[0057] The communication bus mentioned in the aforementioned automatic concrete mix design verification equipment can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc.

[0058] The communication interface is used for communication between the aforementioned automatic concrete mix design verification equipment and other equipment.

[0059] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0060] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0061] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0062] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0063] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0064] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0065] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0066] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0067] In addition, for technical details not described in detail in this embodiment, please refer to the automatic concrete mix design method provided in any embodiment of the present invention, which will not be repeated here.

[0068] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0069] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0070] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0071] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

[0072] It is understood that the system provided in the embodiments of the present invention corresponds to the method provided in the embodiments of the present invention, and the explanation, examples and beneficial effects of the relevant content can be referred to the corresponding parts of the above methods.

Claims

1. A method for automatically verifying concrete mix proportions, characterized in that, The automatic concrete mix design verification method includes: The original mix proportion parameters of the concrete mix to be checked are collected, and the dynamic interference parameters on site are collected in real time through sensors. The dynamic interference parameters include the real-time performance parameters of raw materials and the real-time parameters of construction conditions. On-site performance tests were conducted on actual concrete mixtures to obtain measured work performance data and initial strength data. The compressive strength was simulated using a strength prediction model based on the original mix proportions and the on-site dynamic environmental parameters to obtain theoretical strength data. The measured working performance data and the initial strength data are compared with the theoretical strength data to obtain the strength verification results; Based on the on-site dynamic interference parameters, the corresponding verification rules are called from the preset verification rule library. The verification rules include environmental adaptability intensity threshold, working condition matching performance range, material usage limit and durability index. Automatic verification is performed based on the strength verification results, the verification rules, and the original proportioning parameters; The on-site performance testing of the actual concrete mixture to obtain measured workability data and initial strength data includes: The test items are determined based on the set project type. The test items include at least the slump, spread, initial setting time, and initial strength of structural concrete, and the additional pressure bleeding rate of pumped concrete. A slump test was conducted on the actual concrete mixture to obtain a reference slump. Obtain the current ambient temperature during the field performance test; If the current ambient temperature does not meet the preset conditions, the reference slump is corrected to obtain a corrected slump. The corrected slump is used as measured performance data, and the correction formula is as follows: S 修正 =S 参考 ×[1+0.01×(20 T)]; Among them, S 修正 S represents the corrected slump. 参考 The reference slump is represented by T, and the current ambient temperature is represented by T. The compressive strength was tested using a compression testing machine to obtain the initial strength data; The automatic verification based on the strength verification result, the verification rules, and the original proportioning parameters includes: The environmental adaptability strength threshold, cement dosage limit, and durability index threshold are determined according to the aforementioned verification rules. The strength deviation rate is determined based on the environmental adaptability strength threshold and the strength verification results to complete the strength verification; The amount of cement in the original proportioning parameters is compared with the cement content limit to complete the material content verification; The durability index value is calculated based on the original proportioning parameters, and the durability index value is compared with the durability index threshold to complete the durability verification.

2. The automatic concrete mix design verification method as described in claim 1, characterized in that, The method further includes: Collect historical engineering datasets and use these datasets as features as input; The correlation coefficient of the input features is determined by the Pearson correlation coefficient, and the input features with correlation coefficients greater than the preset coefficient are retained to obtain the target engineering dataset; The target engineering dataset is divided into a training set and a validation set. An LSTM deep learning model is selected and the Adam optimizer is used. The initial learning rate is 0.001, which decays by 10% every 50 rounds. The loss function is the mean squared error (MSE). The network structure includes an input layer, a hidden layer, and an output layer. The model is trained using the training set and its performance is evaluated using the validation set. Training stops when the mean absolute error is less than a preset error, thus obtaining the intensity prediction model.

3. The automatic concrete mix design verification method as described in claim 1, characterized in that, The step of calling the corresponding verification rules from the preset verification rule base based on the on-site dynamic interference parameters includes: The on-site dynamic interference parameters are preprocessed, and the real-time performance parameters of raw materials included in the preprocessed on-site dynamic interference parameters are classified. The corresponding rule set is located by matching the parameter range in the preset verification rule base with the real-time performance parameters of the classified raw materials. The rule set is threshold-corrected based on the construction conditions included in the on-site dynamic interference parameters; Invoke the verification rules from the revised rule set.

4. The automatic concrete mix design verification method as described in claim 3, characterized in that, The threshold correction of the rule set based on the construction conditions included in the on-site dynamic interference parameters includes: The influence weight values ​​of the on-site dynamic disturbance parameters are determined by the analytic hierarchy process (AHP). These influence weight values ​​include the weight of sand and gravel moisture content, the weight of ambient temperature, the weight of transportation distance, the weight of cement temperature, and the weight of aggregate gradation fluctuation. Calculate the comprehensive interference coefficient based on the aforementioned influence weight values; The correction intensity level is determined based on the comprehensive interference coefficient; Based on the correction intensity level and the influence weight value, several parameters with the largest influence weight are selected, and the threshold of each verification rule in the rule set is corrected based on the several parameters with the largest influence weight.

5. The automatic concrete mix design verification method according to any one of claims 1 to 4, characterized in that, The method further includes: Calculate the sensitivity coefficient corresponding to each parameter in the original proportioning parameters; The parameter adjustment priority is determined based on the sensitivity coefficient; The parameter adjustment amount is determined based on the automatic verification results; The original proportioning parameters are adjusted according to the parameter adjustment priority and the parameter adjustment amount.

6. An automatic concrete mix design verification device, used to implement the method described in any one of claims 1-5, characterized in that, The automatic concrete mix design verification device includes: The data acquisition module is used to acquire the original mix proportion parameters of the concrete mix to be checked, and to acquire the dynamic interference parameters on site in real time through sensors. The dynamic interference parameters include the real-time performance parameters of raw materials and the real-time parameters of construction conditions. The testing module is used to conduct on-site performance tests on actual concrete mixtures to obtain measured work performance data and initial strength data. The simulation module is used to perform compressive strength simulation on the original mix proportion parameters and the on-site dynamic environmental parameters through a strength prediction model to obtain theoretical strength data; The verification module is used to compare the measured working performance data and the initial strength data with the theoretical strength data to obtain the strength verification result; The calling module is used to call the corresponding verification rules from the preset verification rule library based on the on-site dynamic interference parameters. The verification rules include environmental adaptability intensity threshold, working condition matching performance range, material usage limit and durability index. The verification module is used to perform automatic verification based on the strength verification results, the verification rules, and the original proportioning parameters.

7. An automatic concrete mix proportion verification device, characterized in that, The automatic concrete mix design verification device includes: a memory, a processor, and an automatic concrete mix design verification program stored in the memory and executable on the processor, wherein the automatic concrete mix design verification program is configured to implement the steps of the automatic concrete mix design verification method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores an automatic concrete mix design verification program, which, when executed by a processor, implements the steps of the automatic concrete mix design verification method as described in any one of claims 1 to 5.

Images