A process optimization management method and system for soil heavy metal detection

Abstract

The application discloses a process optimization management method and system for soil heavy metal detection, and relates to the technical field of heavy metal detection. The application obtains historical heavy metal pretreatment records, establishes a standardized pretreatment process and a multi-factor abnormal correlation model based on the historical heavy metal pretreatment records, obtains sample basic information of a target detection area, matches the sample basic information with each standardized pretreatment process, adjusts the corresponding standardized pretreatment process and the multi-factor abnormal correlation model according to a matching result, further outputs a soil heavy metal detection decision, executes the soil heavy metal detection decision, collects real-time detection process data in the execution process of the soil heavy metal detection decision, judges whether there is a detection process abnormality through the standardized pretreatment process and the multi-factor abnormal correlation model, and re-executes a corresponding process stage in the soil heavy metal detection decision according to a judgment result.

Description

Technical Field

[0001] This invention relates to the field of heavy metal detection technology, specifically to a process optimization management method and system for heavy metal detection in soil. Background Technology

[0002] Heavy metal pollution in soil has become a global environmental problem. Excessive accumulation of heavy metals such as lead, mercury, and cadmium can damage soil ecological functions, threaten biodiversity, and harm human health through the food chain. Current methods for detecting heavy metals in soil face challenges such as long detection times, complex operations, and cumbersome data analysis. While traditional methods such as atomic absorption spectrometry and inductively coupled plasma mass spectrometry are widely used, their cumbersome and time-consuming pretreatment processes affect detection efficiency and accuracy.

[0003] Soil heavy metal testing is a crucial step in environmental monitoring and remediation, and the accuracy and timeliness of the results directly affect the reliability of pollution assessments and the scientific basis of remediation decisions. Traditional testing procedures rely heavily on fixed manual operating standards and experience-based judgment. From sample collection and pretreatment (such as digestion and volume adjustment) to instrumental analysis, the process involves numerous steps and is highly dependent on the operator's proficiency. Due to the complexity of the soil matrix and the presence of many interfering factors (such as organic matter content, pH value, and moisture), standardized pretreatment procedures are difficult to apply universally to all samples. Inappropriate procedure selection or parameter mismatch can introduce systematic errors, leading to biased test results or poor reproducibility. Furthermore, the entire process lacks effective real-time monitoring and anomaly tracing mechanisms. Once a deviation occurs at any stage (such as abnormal digestion temperature or incorrect reagent addition), it is often only discovered during the final data analysis stage or even after the report is issued, resulting in wasted samples and time, severely impacting testing efficiency and laboratory operating costs.

[0004] Current technologies lack the ability to deeply correlate and model historical processing data, sample characteristics, and process anomalies. They cannot adaptively match and fine-tune optimal pretreatment schemes based on different sample types (such as farmland soil and industrial site soil), nor can they provide early warnings and process self-correction at the initial stage of anomalies. Therefore, there is an urgent need for a detection process optimization management method that integrates historical data mining, intelligent decision-making, and real-time process control to improve the overall quality control level, automation level, and operational efficiency of soil heavy metal detection. This paper presents a process optimization management method and system for soil heavy metal detection. Summary of the Invention

[0005] The purpose of this invention is to provide a process optimization management method and system for heavy metal detection in soil, so as to solve the problems in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: A process optimization management method for heavy metal detection in soil includes the following steps: Step S1: Obtain historical heavy metal pretreatment records, establish a standardized pretreatment process and a multi-factor anomaly correlation model based on the historical heavy metal pretreatment records; Step S2: Obtain basic sample information of the target detection area, match the basic sample information with each standardized preprocessing process, adjust the corresponding standardized preprocessing process and multi-factor anomaly correlation model according to the matching results, and then output soil heavy metal detection decision. Step S3: Execute soil heavy metal detection decision. During the execution of the soil heavy metal detection decision, collect real-time detection process data. Determine whether there is any abnormality in the detection process through a standardized preprocessing process and a multi-factor anomaly correlation model. Based on the judgment result, re-execute the corresponding process stage in the soil heavy metal detection decision.

[0007] Furthermore, obtaining historical heavy metal pretreatment records includes: Historical heavy metal pretreatment records of the target detection area are collected via the Internet. These records are categorized into four stages: sampling, grinding, digestion, and volume adjustment. Furthermore, records within each stage are split according to the type of process node to form a node data pool.

[0008] Furthermore, the process of establishing a standardized preprocessing workflow based on historical heavy metal preprocessing records, and the process of developing a multi-factor anomaly correlation model, includes: Extract all process nodes under normal operating conditions in each process stage from the node data pool, perform statistical analysis on multiple normal data of the same process node, and use the mean method combined with variance screening to obtain the optimal parameter range of each process node. According to the process sequence of soil heavy metal pretreatment, the normal process nodes of each process stage are combined in series and parallel to generate a process link. Starting from the process node of the sampling stage, the process nodes of the grinding, digestion and volume fixation stages are connected in sequence to generate a standardized pretreatment process. Extract node data for all abnormal operating conditions from the node data pool, identify abnormal process nodes under each abnormal scenario, perform correlation analysis on the abnormal process nodes, obtain the causal relationship between core abnormal process nodes and secondary abnormal process nodes in the abnormal scenario, and construct an independent multi-factor abnormal correlation model for each abnormal scenario.

[0009] Furthermore, the process of matching basic sample information with various standardized preprocessing procedures, and adjusting the corresponding standardized preprocessing procedures and multi-factor anomaly correlation models based on the matching results, includes: On-site detection of the target detection area is carried out to generate corresponding sample basic information. The sample basic information is matched with the corresponding standardized pre-processing process to obtain the matching degree between the sample basic information and each standardized process. A matching degree threshold is set. Based on the relationship between the matching degree and the matching degree threshold, the standardized pre-processing process is used as the basic detection process. Based on the soil type, heavy metal type, and testing equipment model covered by the basic testing process, retrieve the matching multi-factor anomaly correlation model; The basic detection process is linked with the multi-factor anomaly association model to establish an association mapping relationship between process nodes and multi-factor anomaly association models. That is, each process node in the basic detection process contains all the multi-factor anomaly association models of the corresponding process node in the multi-factor anomaly association model library.

[0010] Furthermore, the process of generating decisions regarding soil heavy metal detection includes: The decision-making process for soil heavy metal detection includes an integrated implementation plan encompassing detection procedures, anomaly prevention and control, and equipment and reagent allocation. Based on the standardized pretreatment process and multi-factor anomaly correlation model, the execution order of each process stage, the parameter requirements of each process node, and the early warning threshold of key nodes are clarified. At the same time, the equipment model, operating status requirements, reagent types, addition sequence and dosage, as well as the execution standards and duration requirements of each operation step are determined.

[0011] Furthermore, the process of collecting real-time detection process data during the implementation of soil heavy metal detection decisions includes: In accordance with the operational guidelines for soil heavy metal testing decisions, the four process stages of sampling, grinding, digestion, and volume adjustment were carried out sequentially, following the parameter requirements and operational steps of each process node. During the execution of the testing process, real-time data collection of process nodes at each stage is allocated to form a real-time testing process data pool. The real-time detection process data covers all real-time data from the detection equipment node, reagent node, processing operation node, and heavy metal node.

[0012] Furthermore, by standardizing the preprocessing procedures and using a multi-factor anomaly correlation model to determine whether there are any anomalies in the detection process, and based on the determination results, re-executing the corresponding process stage in the soil heavy metal detection decision-making process includes: The real-time detection process data is compared with the optimal parameter range of the corresponding process node in the standardized pre-processing process. Based on the comparison results, it is determined whether the process node is operating normally, and the detection process continues to advance. If the real-time detection process data of a process node is not within the optimal parameter range, then according to the causal relationship of the corresponding process node, the corresponding multi-factor anomaly association model is retrieved from the soil heavy metal detection decision, and the corresponding real-time detection process data is recorded as real-time anomaly data. Real-time abnormal data is input into a multi-factor abnormality association model for model matching and abnormality diagnosis to determine the degree of abnormality, cause of abnormality, core abnormal process nodes and scope of abnormality. If the matching degree between real-time abnormal data and a certain abnormality model reaches a preset threshold, it is determined that there is a corresponding type of abnormality in the detection process; if no corresponding multi-factor abnormality association model is matched, it is determined to be a new type of abnormality scenario. If a new abnormal scenario is identified, the current detection process is immediately stopped, and technical personnel are notified to conduct manual review and anomaly analysis, formulate a targeted handling plan, correct the error, and re-execute the corresponding process stage. At the same time, real-time abnormal data is automatically recorded and step S1 is repeated to update the multi-factor anomaly association model library. If the testing process is deemed normal, the subsequent process stages will continue until the entire soil heavy metal pretreatment process is completed and the final test sample is output.

[0013] A process optimization management system for soil heavy metal detection includes a detection process analysis module, a process decision construction module, and a decision execution optimization module. The detection process analysis module is used to obtain historical heavy metal pretreatment records, establish a standardized pretreatment process based on the historical heavy metal pretreatment records, and a multi-factor anomaly correlation model. The process decision construction module is used to obtain basic sample information of the target detection area, match the basic sample information with each standardized preprocessing process, adjust the corresponding standardized preprocessing process and multi-factor anomaly correlation model according to the matching results, and then output soil heavy metal detection decision. The decision execution optimization module is used to execute soil heavy metal detection decisions. During the execution of soil heavy metal detection decisions, it collects real-time detection process data, judges whether there are any abnormalities in the detection process through a standardized preprocessing process and a multi-factor anomaly correlation model, and re-executes the corresponding process stage in the soil heavy metal detection decision based on the judgment result.

[0014] The technical effects and advantages provided by the present invention in the above technical solution are as follows: 1. By constructing a standardized pretreatment process library and a multi-factor anomaly correlation model, this invention can intelligently match and allocate the optimal pretreatment scheme and corresponding risk warning model based on the specific basic information of the target soil sample. This achieves personalization and precision of the pretreatment process, reduces systematic errors caused by improper process selection from the source, and significantly improves the accuracy and comparability of test results for soil samples with different matrices.

[0015] 2. This invention collects process data in real time while executing testing decisions and uses standardized processes and anomaly models for online judgment. Once a process deviation or abnormal sign is detected, it automatically guides the re-execution of the corresponding process or adjusts the parameters. This achieves a shift from passive recording to proactive intervention, significantly advancing the problem discovery and handling points, effectively avoiding batch errors or sample rejection, shortening the testing cycle, and improving the overall throughput and reliability of laboratory results. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0017] Figure 1 This is a flowchart of the method of the present invention.

[0018] Figure 2 This is a system block diagram of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0020] Please see Figure 1 As shown, a process optimization management method for heavy metal detection in soil includes the following steps: Step S1: Obtain historical heavy metal pretreatment records, establish a standardized pretreatment process and a multi-factor anomaly correlation model based on the historical heavy metal pretreatment records; Step S2: Obtain basic sample information of the target detection area, match the basic sample information with each standardized preprocessing process, adjust the corresponding standardized preprocessing process and multi-factor anomaly correlation model according to the matching results, and then output soil heavy metal detection decision. Step S3: Execute soil heavy metal detection decision. During the execution of the soil heavy metal detection decision, collect real-time detection process data. Determine whether there is any abnormality in the detection process through a standardized preprocessing process and a multi-factor anomaly correlation model. Based on the judgment result, re-execute the corresponding process stage in the soil heavy metal detection decision.

[0021] Furthermore, step S1 is implemented through the following process: Step S101: Obtain historical heavy metal pretreatment records. The specific process includes: Historical heavy metal pretreatment records for the past 5 years were collected from the target detection area via the Internet. The records cover different soil types, different heavy metal species, different detection equipment models, and different operators. The historical heavy metal pretreatment records include the detection equipment operating parameters, reagent usage information, operation steps, raw heavy metal detection data, abnormal problem records, and abnormal handling results for each process stage. Historical heavy metal pretreatment records are categorized into four process stages: sampling, grinding, digestion, and volume adjustment. Records within each process stage are further divided according to process node type, forming a node data pool. This node data pool contains several process nodes, including detection equipment nodes (describing the operating status of the detection equipment, such as equipment rotation speed), reagent nodes (identifying the addition sequence and dosage of various detection reagents), processing operation nodes (recording equipment operation actions), and heavy metal nodes (recording the types of heavy metals). The node data pool is standardized by converting parameters with different units and dimensions into uniform and comparable values. For example, the rotation speed of the grinding equipment in revolutions per minute and the digestion temperature in degrees Celsius are normalized according to a preset ratio.

[0022] Step S102: Establish a standardized preprocessing workflow and a multi-factor anomaly correlation model based on historical heavy metal preprocessing records. The specific process includes: Extract all process nodes under normal operating conditions in each process stage from the node data pool, perform statistical analysis on multiple normal data of the same process node, and use the mean method combined with variance screening to obtain the optimal parameter range of each process node. Determine the standard operating range of the detection equipment node, the standard addition specifications of the reagent node, the standard execution requirements of the processing operation node, and the standard detection attributes of the heavy metal node under normal operating conditions. According to the process sequence of soil heavy metal pretreatment, the normal process nodes of each process stage are combined in series and parallel to generate a process link. Starting from the process node of the sampling stage, the process nodes of grinding, digestion and volume fixation stages are connected in sequence. Among them, the series nodes are the necessary steps in the process, and the parallel nodes are optional adaptive steps for different heavy metal types. After the process nodes are combined, the entire process link is simulated and verified. The detection requirements of conventional soil samples are input to verify the matching of parameters of each node and the smoothness of the connection between process stages. If there are no parameter conflicts or process blockages during the simulation, the process link is recorded as a standardized pre-processing process. If there are parameter conflicts or process bottlenecks, the optimal parameter range of the corresponding process node will be reset and re-simulated and verified until the process requirements of normal working conditions are met. Finally, the preprocessing process will be standardized, and the optimal parameter range of each process node and the correlation logic between process nodes will be marked in the standardized preprocessing process. The correlation logic includes progressive operation, parallel operation, etc. Extract node data for all abnormal operating conditions from the node data pool, combine it with abnormal problem records, identify abnormal process nodes under each abnormal scenario, and clarify the specific abnormal behavior of the abnormal process nodes (such as grinding equipment speed below the standard threshold, insufficient addition of digestion reagent, and excessive shaking time during volume adjustment). Correlation analysis is performed on abnormal process nodes to obtain the causal relationship between core abnormal process nodes and secondary abnormal process nodes in abnormal scenarios. For example, incorrect reagent dosage will lead to insufficient digestion, which in turn will cause abnormal heavy metal detection signals. The reagent node is the core abnormal process node, while the digestion equipment node and heavy metal node are secondary abnormal process nodes. For each abnormal scenario, an independent multi-factor abnormal association model is constructed, and all abnormal process nodes in the corresponding scenario are connected in series and parallel according to causal relationship. The abnormal threshold and influence weight of each abnormal process node are marked. At the same time, a corresponding abnormal handling plan is matched for each model, and the process correction measures starting from the core abnormal process node are clarified. All constructed multi-factor anomaly association models are classified and organized. They are divided into sampling anomaly models, grinding anomaly models, resolving anomaly models, and stabilizing anomaly models according to the process stage of anomaly occurrence. They are also divided into mild anomaly models, moderate anomaly models, and severe anomaly models according to the degree of anomaly impact, forming a multi-factor anomaly association model library to achieve rapid retrieval and matching of anomaly scenarios.

[0023] Furthermore, step S2 is implemented through the following process: Step S201: Match the basic information of the sample with each standardized preprocessing procedure, and adjust the corresponding standardized preprocessing procedure and multi-factor anomaly correlation model according to the matching results. The specific process includes: On-site testing is conducted on the target detection area to generate corresponding basic sample information, which includes key parameters such as soil type, pH value, and organic matter content. The basic sample information is matched with the corresponding standardized pretreatment process to obtain the matching degree between the basic sample information and each standardized process. The matching degree is accumulated by using the percentage difference of each value in each basic sample information as the single matching degree. The single matching degree of key parameters with different terms (such as soil type) is recorded as 0, otherwise it is recorded as 1. Set a matching threshold. If the matching degree of a unique standardized pretreatment procedure is found to be higher than the threshold, the corresponding standardized pretreatment procedure is determined as the basic detection procedure for the target sample. If the matching degree of multiple standardized pretreatment procedures is found to be higher than the threshold, the standardized pretreatment procedure with the highest matching degree is selected as the basic detection procedure. If the matching degree of all standardized pretreatment procedures is lower than the threshold, the standardized pretreatment procedure with the highest matching degree is used as the basis, and the parameters of its process nodes are adjusted according to the basic information of the sample to form a customized standardized pretreatment procedure adapted to the target sample, which serves as the basic detection procedure. Based on the established basic testing process library, the corresponding process links are retrieved. At the same time, based on the soil type, heavy metal type and testing equipment model covered by the basic testing process, the matching multi-factor anomaly association model is retrieved from the multi-factor anomaly association model library, including mild, moderate and severe anomaly models that may occur in the corresponding process stage. The basic detection process is linked with the multi-factor anomaly association model to establish an association mapping relationship between process nodes and multi-factor anomaly association models. That is, each process node in the basic detection process contains all the multi-factor anomaly association models of the corresponding process node in the multi-factor anomaly association model library. Based on the linkage configuration results, the standardized pre-processing process is optimized and adjusted. Key nodes prone to anomalies are marked in the process chain, and anomaly warning thresholds for key nodes are preset to provide a basis for anomaly monitoring in subsequent detection processes.

[0024] Step S202: Output soil heavy metal detection decision, the specific process includes: The soil heavy metal detection decision includes an integrated execution plan encompassing detection procedures, anomaly prevention and control, and equipment and reagent allocation. It mainly consists of five parts: basic detection procedures, corresponding anomaly models, equipment operating parameters, reagent usage plans, and operational execution specifications. Based on the standardized pretreatment process and multi-factor anomaly correlation model, the execution order of each process stage, the parameter requirements of each process node, and the early warning threshold of key nodes are clarified. At the same time, the equipment model, operating status requirements, reagent types, addition sequence and dosage, as well as the execution standards and duration requirements of each operation step are determined.

[0025] Furthermore, step S3 is implemented through the following process: Step S301: Execute soil heavy metal detection decision-making. During the execution of the soil heavy metal detection decision-making process, real-time detection process data is collected. The specific process includes: Based on the decision on soil heavy metal testing, the testing equipment was debugged and the reagents were prepared to ensure that the operating parameters of the testing equipment met the decision requirements and that the types, concentrations and shelf lives of the reagents met the usage specifications. Operators followed the operational guidelines in the decision-making process for soil heavy metal testing, sequentially performing the four stages of sampling, grinding, digestion, and volume adjustment, adhering to the parameter requirements and operational steps for each stage. During the execution of the testing process, real-time data collection of process nodes at each stage is allocated to form a real-time testing process data pool. The real-time detection process data covers all real-time data from the detection equipment node, reagent node, processing operation node, and heavy metal node. The detection equipment node data includes operating parameters such as equipment speed, temperature, pressure, and liquid level. The reagent node data includes usage parameters such as reagent addition time, dosage, and remaining amount. The processing operation node data includes process parameters such as operation execution time, number of executions, and operation duration. The heavy metal node data includes detection parameters such as heavy metal detection signal intensity and preliminary detection concentration.

[0026] Step S302: Determine whether there are any abnormalities in the detection process through the standardized preprocessing procedure and the multi-factor anomaly correlation model. Based on the determination result, re-execute the corresponding process stage in the soil heavy metal detection decision-making. The specific process includes: The real-time detection process data is compared with the optimal parameter range of the corresponding process node in the standardized pre-processing process. If the real-time data are all within the optimal parameter range, the process node is judged to be operating normally, and the detection process continues. If the real-time detection process data of a process node is not within the optimal parameter range, then according to the causal relationship of the corresponding process node, the corresponding multi-factor anomaly association model is retrieved from the soil heavy metal detection decision, and the corresponding real-time detection process data is recorded as real-time anomaly data. Real-time abnormal data is input into a multi-factor abnormality association model for model matching and abnormality diagnosis. The degree of abnormality (mild / moderate / severe), cause of abnormality, core abnormal process nodes, and scope of abnormality impact are determined. If the matching degree between real-time abnormal data and a certain abnormality model reaches a preset threshold, it is determined that there is a corresponding type of abnormality in the detection process. If no corresponding multi-factor abnormality association model is matched, it is determined to be a new type of abnormality scenario. The real-time abnormal data is automatically recorded and the process of step S1 is repeated to update the multi-factor abnormality association model library. If the testing process is found to be normal, the subsequent process stages will continue until the entire soil heavy metal pretreatment process is completed and the final test sample is output. If a minor anomaly is detected in the detection process and the anomaly does not affect subsequent process stages, the parameters of the current abnormal process node are corrected in real time according to the anomaly handling scheme corresponding to the multi-factor anomaly association model. After the correction is completed, the current process stage continues to be executed without re-execution. If it is determined that there is a moderate or severe abnormality in the testing process, and the abnormality has caused irreversible impact on the current process stage, or may affect the testing results of subsequent process stages, then the current testing process shall be stopped immediately. Based on the abnormality diagnosis results, the unqualified products of the current process stage shall be removed, and all operations of the corresponding process stage in the soil heavy metal testing decision shall be re-executed from the starting process node of the process stage where the abnormality occurred. If a new abnormal scenario is identified, the current detection process should be stopped immediately, and technical personnel should be notified to conduct manual review and anomaly analysis, formulate a targeted handling plan, correct the error, and re-execute the corresponding process stage. At the same time, real-time abnormal data should be automatically recorded and step S1 should be repeated to update the multi-factor anomaly association model library.

[0027] Please see Figure 2 As shown, a process optimization management system for soil heavy metal detection includes a detection process analysis module, a process decision construction module, and a decision execution optimization module. The detection process analysis module is used to obtain historical heavy metal pretreatment records, establish a standardized pretreatment process based on the historical heavy metal pretreatment records, and a multi-factor anomaly correlation model. The process decision construction module is used to obtain basic sample information of the target detection area, match the basic sample information with each standardized preprocessing process, adjust the corresponding standardized preprocessing process and multi-factor anomaly correlation model according to the matching results, and then output soil heavy metal detection decision. The decision execution optimization module is used to execute soil heavy metal detection decisions. During the execution of soil heavy metal detection decisions, it collects real-time detection process data, judges whether there are any abnormalities in the detection process through a standardized preprocessing process and a multi-factor anomaly correlation model, and re-executes the corresponding process stage in the soil heavy metal detection decision based on the judgment result.

[0028] 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 technical scope 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.

Claims

1. A process optimization management method for heavy metal detection in soil, characterized in that, Includes the following steps: Step S1: Obtain historical heavy metal pretreatment records, establish a standardized pretreatment process and a multi-factor anomaly correlation model based on the historical heavy metal pretreatment records; Step S2: Obtain basic sample information of the target detection area, match the basic sample information with each standardized preprocessing process, adjust the corresponding standardized preprocessing process and multi-factor anomaly correlation model according to the matching results, and then output soil heavy metal detection decision. Step S3: Execute soil heavy metal detection decision. During the execution of the soil heavy metal detection decision, collect real-time detection process data. Determine whether there is any abnormality in the detection process through a standardized preprocessing process and a multi-factor anomaly correlation model. Based on the judgment result, re-execute the corresponding process stage in the soil heavy metal detection decision.

2. The process optimization management method for soil heavy metal detection according to claim 1, characterized in that, Historical heavy metal pretreatment records include: Historical heavy metal pretreatment records of the target detection area are collected via the Internet. These records are categorized into four stages: sampling, grinding, digestion, and volume adjustment. Furthermore, records within each stage are split according to the type of process node to form a node data pool.

3. The process optimization management method for soil heavy metal detection according to claim 2, characterized in that, The process of establishing a standardized preprocessing workflow based on historical heavy metal preprocessing records, and the development of a multi-factor anomaly correlation model, includes: Extract all process nodes under normal operating conditions in each process stage from the node data pool, perform statistical analysis on multiple normal data of the same process node, and use the mean method combined with variance screening to obtain the optimal parameter range of each process node. According to the process sequence of soil heavy metal pretreatment, the normal process nodes of each process stage are combined in series and parallel to generate a process link. Starting from the process node of the sampling stage, the process nodes of the grinding, digestion and volume fixation stages are connected in sequence to generate a standardized pretreatment process. Extract node data for all abnormal operating conditions from the node data pool, identify abnormal process nodes under each abnormal scenario, perform correlation analysis on the abnormal process nodes, obtain the causal relationship between core abnormal process nodes and secondary abnormal process nodes in the abnormal scenario, and construct an independent multi-factor abnormal correlation model for each abnormal scenario.

4. The process optimization management method for soil heavy metal detection according to claim 3, characterized in that, The process of matching basic sample information with various standardized preprocessing procedures, and adjusting the corresponding standardized preprocessing procedures and multi-factor anomaly correlation models based on the matching results includes: On-site detection of the target detection area is carried out to generate corresponding sample basic information. The sample basic information is matched with the corresponding standardized pre-processing process to obtain the matching degree between the sample basic information and each standardized process. A matching degree threshold is set. Based on the relationship between the matching degree and the matching degree threshold, the standardized pre-processing process is used as the basic detection process. Based on the soil type, heavy metal type, and testing equipment model covered by the basic testing process, retrieve the matching multi-factor anomaly correlation model; The basic detection process is linked with the multi-factor anomaly association model to establish an association mapping relationship between process nodes and multi-factor anomaly association models. That is, each process node in the basic detection process contains all the multi-factor anomaly association models of the corresponding process node in the multi-factor anomaly association model library.

5. The process optimization management method for heavy metal detection in soil according to claim 4, characterized in that, The process of generating decisions on soil heavy metal detection includes: The decision-making process for soil heavy metal detection includes an integrated implementation plan encompassing detection procedures, anomaly prevention and control, and equipment and reagent allocation. Based on the standardized pretreatment process and multi-factor anomaly correlation model, the execution order of each process stage, the parameter requirements of each process node, and the early warning threshold of key nodes are clarified. At the same time, the equipment model, operating status requirements, reagent types, addition sequence and dosage, as well as the execution standards and duration requirements of each operation step are determined.

6. The process optimization management method for heavy metal detection in soil according to claim 5, characterized in that, The process of collecting real-time detection process data during the implementation of soil heavy metal detection decisions includes: In accordance with the operational guidelines for soil heavy metal testing decisions, the four process stages of sampling, grinding, digestion, and volume adjustment were carried out sequentially, following the parameter requirements and operational steps of each process node. During the execution of the testing process, real-time data collection of process nodes at each stage is allocated to form a real-time testing process data pool. The real-time detection process data covers all real-time data from the detection equipment node, reagent node, processing operation node, and heavy metal node.

7. The process optimization management method for heavy metal detection in soil according to claim 6, characterized in that, The process of determining whether there are abnormalities in the detection process through standardized preprocessing procedures and multi-factor anomaly correlation models, and then re-executing the corresponding process stage in the soil heavy metal detection decision-making based on the determination results, includes: The real-time detection process data is compared with the optimal parameter range of the corresponding process node in the standardized pre-processing process. Based on the comparison results, it is determined whether the process node is operating normally, and the detection process continues to advance. If the real-time detection process data of a process node is not within the optimal parameter range, then according to the causal relationship of the corresponding process node, the corresponding multi-factor anomaly association model is retrieved from the soil heavy metal detection decision, and the corresponding real-time detection process data is recorded as real-time anomaly data. Real-time abnormal data is input into a multi-factor abnormality association model for model matching and abnormality diagnosis to determine the degree of abnormality, cause of abnormality, core abnormal process nodes and scope of abnormality. If the matching degree between real-time abnormal data and a certain abnormality model reaches a preset threshold, it is determined that there is a corresponding type of abnormality in the detection process; if no corresponding multi-factor abnormality association model is matched, it is determined to be a new type of abnormality scenario. If the testing process is deemed normal, the subsequent process stages will continue until the entire soil heavy metal pretreatment process is completed and the final test sample is output.

8. A process optimization management system for soil heavy metal detection, used to implement the process optimization management method for soil heavy metal detection as described in any one of claims 1-7, characterized in that, It includes a detection process analysis module, a process decision construction module, and a decision execution optimization module; The detection process analysis module is used to obtain historical heavy metal pretreatment records, establish a standardized pretreatment process based on the historical heavy metal pretreatment records, and a multi-factor anomaly correlation model. The process decision construction module is used to obtain basic sample information of the target detection area, match the basic sample information with each standardized preprocessing process, adjust the corresponding standardized preprocessing process and multi-factor anomaly correlation model according to the matching results, and then output soil heavy metal detection decision. The decision execution optimization module is used to execute soil heavy metal detection decisions. During the execution of soil heavy metal detection decisions, it collects real-time detection process data, judges whether there are any abnormalities in the detection process through a standardized preprocessing process and a multi-factor anomaly correlation model, and re-executes the corresponding process stage in the soil heavy metal detection decision based on the judgment result.

Images