A method and system for risk assessment of the whole life cycle of laboratory chemicals

Abstract

This invention relates to the field of chemical control technology and discloses a method and system for risk assessment of the entire life cycle of laboratory chemicals. Through storage incompatibility analysis, this invention achieves accurate identification, classification, isolation, and control of risks associated with incompatible storage. It also quantifies and records the degradation process of chemicals accumulated during long-term storage through environmental stress degradation analysis, providing a realistic degradation baseline for subsequent stages. By extracting key feature information from experimental record data and dynamic parameters, the impact of the experimental process on the subsequent stability of waste is transformed into structured data. Finally, the final test data, hazardous characteristic time-series data, and process influencing factor set are integrated to conduct risk evolution simulation, enabling forward-looking prediction of risk evolution trends during waste storage. This invention, through the quantitative transmission and integration of risk information throughout the entire life cycle, solves the problem of inaccurate risk assessments caused by independent assessments and fragmented information in traditional methods.

Description

Technical Field

[0001] This invention relates to the field of chemical control technology, and in particular to a method and system for risk assessment of the entire life cycle of laboratory chemicals. Background Technology

[0002] Risk assessment of the entire lifecycle of laboratory chemicals aims to cover all stages of chemicals from access storage and testing to final disposal through an executable automated technical process. It involves collecting, analyzing, and modeling multi-source heterogeneous data generated at each stage. Its core purpose is to identify and quantify potential safety risks arising from changes in chemical state, environmental exposure, and operational processes within and between each stage, based on physicochemical mechanisms and quantitative algorithms. This allows for the automatic triggering of risk warnings and coordinated implementation of control measures based on dynamic feedback from real-time data.

[0003] Existing laboratory chemical risk assessment methods typically assess each stage independently based on the current state of the chemical. However, the storage history of a chemical during the warehousing stage and the additional impacts it experiences during experimental operations can have a substantial impact on its subsequent risks. Because traditional methods fail to pass on this historical information to subsequent stages, subsequent risk assessments lack key input data and cannot reflect the true risk status of the chemical after its complete life cycle, resulting in inaccurate risk assessments. Summary of the Invention

[0004] The main objective of this invention is to provide a method and system for risk assessment of the entire life cycle of laboratory chemicals, aiming to solve the technical problems in the prior art.

[0005] This invention proposes a risk assessment method for the entire life cycle of laboratory chemicals, including: Acquire storage data of the target chemical when it is in the storage stage, and perform storage incompatibility analysis and environmental stress degradation analysis based on the storage data to obtain storage incompatibility risk map and time series data of hazardous characteristics; Based on the storage incompatibility risk map and the time series data of the hazardous characteristics, a first control command is generated and issued to the warehouse management actuator to perform preventive adjustments to the classification and isolation storage and environmental parameters; The dynamic parameters of the chemical reaction of the target chemical are obtained when it is in the experimental operation stage, and the dynamic parameters of the chemical reaction are compared with the dynamic risk threshold. Based on the comparison result, a second control command is generated and issued to the emergency execution agency to control the reaction process. Obtain test record data of the target chemical, and obtain a set of process influencing factors based on the test record data and the dynamic parameters of the chemical reaction; Obtain the final test data of chemical waste before the final disposal stage, and perform risk evolution simulation based on the final test data, hazardous characteristic time series data and the process influencing factor set to obtain the temporary storage risk prediction curve of chemical waste; Determine whether the temporary risk prediction curve meets the preset conditions within the preset observation period: If the preset conditions are met, the chemical waste is determined to be in a stable state within the preset observation period and is allowed to enter the regular disposal process. If the preset conditions are not met, a third control command is generated and issued based on the temporary storage risk prediction curve to drive the waste storage cabinet to perform safe disposal measures.

[0006] This application also provides a risk assessment system for the entire life cycle of laboratory chemicals, including: The storage analysis module is used to acquire storage data of the target chemical when it is in the storage stage, and to perform storage incompatibility analysis and environmental stress degradation analysis based on the storage data to obtain storage incompatibility risk map and hazardous characteristic time series data. The warehouse control module is used to generate and issue a first control command to the warehouse management actuator based on the storage incompatibility risk map and the time series data of the hazardous characteristics, so as to perform preventive adjustment of classified and isolated storage and environmental parameters; The test monitoring module is used to acquire the dynamic parameters of the chemical reaction when the target chemical is in the test operation stage, compare the dynamic parameters of the chemical reaction with the dynamic risk threshold, generate and issue a second control command to the emergency execution agency based on the comparison result, so as to control the reaction process; The process quantification module is used to acquire test record data of the target chemical and obtain a set of process influencing factors based on the test record data and the dynamic parameters of the chemical reaction; The risk simulation module is used to obtain the final detection data of chemical waste before the final disposal stage, and to perform risk evolution simulation based on the final detection data, the time series data of hazardous characteristics and the set of process influencing factors to obtain the temporary storage risk prediction curve of chemical waste. The processing execution module is used to determine whether the temporary risk prediction curve meets preset conditions within a preset observation period: If the preset conditions are met, the chemical waste is determined to be in a stable state within the preset observation period and is allowed to enter the regular disposal process. If the preset conditions are not met, a third control command is generated and issued based on the temporary storage risk prediction curve to drive the waste storage cabinet to perform safe disposal measures.

[0007] Preferably, the risk simulation module includes: The data acquisition module is used to acquire the current hazard index quantification value of the chemical waste based on the final detection data, and to acquire the actual deterioration rate of the target chemical at the end of the storage stage based on the hazard characteristic time series data. The degradation correction module is used to correct the actual degradation rate based on the process influencing factor set to obtain the corrected degradation rate. The cumulative extrapolation module is used to perform cumulative extrapolation of the risk index based on the corrected degradation rate and the current risk index quantification value, so as to obtain the predicted risk index quantification value at each prediction time in the future. The curve construction module is used to perform risk quantification mapping on the predicted risk index quantification value to obtain the risk index quantification value at each prediction time in the future, and construct a temporary risk prediction curve with prediction time as the horizontal axis and risk index quantification value as the vertical axis.

[0008] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described risk assessment method for the entire life cycle of laboratory chemicals.

[0009] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described risk assessment method for the entire life cycle of laboratory chemicals.

[0010] The beneficial effects of this invention are as follows: This invention divides the entire life cycle of laboratory chemicals into three stages, conducts targeted data collection and risk assessment at each stage, and constructs a risk information transmission chain that runs through the entire life cycle. In the storage stage, storage incompatibility analysis generates a storage incompatibility risk map, thereby achieving accurate identification, classification, isolation, and control of incompatible storage risks. Simultaneously, environmental stress degradation analysis generates hazardous characteristic time-series data, quantifying and recording the degradation process of chemicals accumulated during long-term storage, providing a true degradation baseline for subsequent stages. In the experimental operation stage, real-time monitoring of dynamic chemical reaction parameters and comparison with dynamic risk thresholds enables immediate intervention in abnormal reactions. Furthermore, key features are extracted from experimental record data and dynamic parameters. This invention transforms the impact of experimental processes such as catalyst residue, thermal shock, and thermal fluctuations on the subsequent stability of chemical waste into structured data. At the final disposal stage, it integrates the final test data, hazardous characteristic time-series data, and process influencing factor set to simulate risk evolution and obtain a temporary storage risk prediction curve. This allows for forward-looking prediction of the risk evolution trend during the temporary storage of chemical waste and automatically generates tiered control commands based on the prediction results to drive the temporary storage cabinet to perform targeted safe disposal. By quantitatively transmitting and integrating risk information throughout the entire lifecycle, this invention solves the problem of inaccurate risk assessment caused by independent assessments and fragmented information at each stage in traditional methods. It not only achieves a shift from passive response to proactive prevention but also significantly improves the accuracy and safety of laboratory chemical risk assessment. Attached Figure Description

[0011] Figure 1 This is a schematic diagram of a method flow according to an embodiment of the present invention.

[0012] Figure 2 This is a schematic diagram of the system structure according to an embodiment of the present invention.

[0013] Figure 3 This is a schematic diagram of the internal structure of a computer device according to an embodiment of this application.

[0014] 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

[0015] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0016] like Figure 1 As shown, this application provides a risk assessment method for the entire life cycle of laboratory chemicals, including: S1. Obtain storage data of the target chemical when it is in the storage stage, and perform storage incompatibility analysis and environmental stress degradation analysis based on the storage data to obtain storage incompatibility risk map and hazardous characteristic time series data.

[0017] For example, this invention divides the entire lifecycle of laboratory chemicals into a storage stage, an experimental operation stage, and a disposal termination stage. The storage stage refers to the period after chemicals are inspected and accepted into the warehouse, during which they are stored and managed in a designated storage area within the laboratory. This storage area is a warehouse equipped with an intelligent management system. This area is typically divided into multiple independently ventilated storage units, such as explosion-proof safety cabinets, ventilated medicine cabinets, gas cylinder cabinets, and open / semi-open shelving areas. The entire storage area is equipped with an environmental monitoring network, including sensors distributed at key locations, linked to storage management actuators, including a regional-level fresh air system. This includes independent ventilation devices and inert gas protection systems at the system and storage unit level; when chemicals are in the storage stage, the storage data of the target chemicals is acquired. The storage data includes chemical ledger data and storage environment data. Among them, chemical ledger data refers to the data recorded in the laboratory chemical inventory management system that reflects the storage status of chemicals, including chemical identification, packaging material, entry time, storage location, etc.; storage environment data refers to the environmental parameter sequence continuously recorded by time stamps by sensors deployed at specific storage locations, including the parameter sequence consisting of temperature, humidity, light intensity, etc. continuously monitored at the storage location.

[0018] It should be noted that this invention obtains the identification information and precise storage location coordinates of all currently stocked chemicals from chemical ledger data and maps them onto a two-dimensional spatial grid. Subsequently, based on the incompatibilities between chemicals with different hazardous properties and the severity of the consequences of mixing them, it performs a comprehensive scan and risk calculation on the adjacency relationships of chemicals between adjacent storage units, ultimately generating a storage incompatibility risk map. This map is presented in the form of a two-dimensional grid, where the horizontal axis represents the shelf number and the vertical axis represents the shelf layer number. The value of each cell in the grid represents the current incompatibility risk score of that storage location. The higher the value, the greater the risk due to the mixing or adjacency of chemicals at that location. By using the storage incompatibility risk map, high-risk areas and specific risk sources in the warehouse layout can be quickly identified, thereby providing accurate decision-making basis for warehouse management.

[0019] Traditional risk assessment methods typically assess risks based solely on the current state of chemicals, neglecting potential risks accumulated during long-term storage, leading to inaccurate risk assessments. Therefore, this invention simulates the evolution of key hazard indicators over time after a specific storage process, using storage environment data and the storage requirements of the target chemical. It outputs a set of time-series data on hazard characteristics, with time as the independent variable and the quantified value of the hazard indicator as the dependent variable. The key hazard indicator refers to a measurable indicator that quantifies the degree of hazard of a chemical. For different chemicals, this indicator can be: the amount of hazardous substances generated, the remaining safety margin, and the current hazard state value.

[0020] Taking diethyl ether as an example, when diethyl ether comes into contact with air, it slowly undergoes an auto-oxidation reaction to generate peroxides. Peroxides are extremely unstable and sensitive to heat, vibration, and friction. When they accumulate to a certain concentration, they may cause an explosion. This is the key hazard indicator that needs to be monitored during the storage of diethyl ether. This invention calculates the amount of peroxides generated daily due to temperature during storage by combining temperature records from storage environment data with the storage requirements of diethyl ether and the peroxide generation pattern. The peroxide value is then calculated as the quantified hazard indicator value for diethyl ether.

[0021] Taking nitrocellulose as an example, nitrocellulose undergoes slow decomposition and releases heat during storage. Once the temperature reaches its auto-accelerating decomposition temperature, the decomposition rate accelerates dramatically, potentially leading to spontaneous combustion or even explosion. This invention calculates the thermal decomposition process of nitrocellulose daily during storage by combining temperature records from storage environment data with storage requirements and thermal decomposition patterns, obtaining the remaining safe storage time. This value is the quantified hazard index value for nitrocellulose. By obtaining time-series data on hazardous characteristics through the above operations, the degradation process of chemicals caused by environmental stress during storage can be quantified. On the one hand, this provides dynamic early warning for storage management; on the other hand, it enables subsequent risk assessments to be calculated based on the actual degradation of the chemicals.

[0022] S2. Based on the storage incompatibility risk map and the time series data of the hazardous characteristics, generate and issue a first control command to the warehouse management actuator to perform preventive adjustment of classified and isolated storage and environmental parameters; For example, the present invention traverses each cell in the stored incompatibility risk map and checks whether the incompatibility risk score at that location exceeds a preset incompatibility risk threshold. If the incompatibility risk score at a certain location is greater than the incompatibility risk threshold, it indicates that there is a serious problem of incompatible storage at that location. For example, if ether and concentrated nitric acid are stored together or in adjacent locations, a classification and isolation storage instruction is immediately generated, and the storage location of the chemicals is adjusted according to the classification and isolation storage instruction. For example, the classification and isolation storage instruction is: separate the ether located at A3-2 from the concentrated nitric acid located at A3-3, and transfer the concentrated nitric acid to position B2-5 (this position has been verified by the system to currently have no incompatible substances and maintain a safe distance from the storage area of ​​flammable materials).

[0023] Simultaneously, by extracting the quantified value of the hazard indicator corresponding to the current moment from the time-series data of hazardous characteristics and comparing it with the preset safety threshold, the system confirms whether the current state is safe. It also checks the predicted values ​​of the hazard indicator over a period of time to determine whether the predicted value at any moment will exceed the safety threshold. If the predicted value at any future moment will exceed the safety threshold, it indicates that the chemical deteriorates too quickly under the current environmental conditions, and environmental intervention is required to slow down the deterioration process. Based on this, the system generates environmental parameter adjustment instructions, such as reducing storage temperature or humidity, and sends the instructions to the warehouse management actuator for execution.

[0024] Taking diethyl ether as an example, the system extracts the current peroxide value from the hazardous characteristic time series data. The value is 38 ppm, which is lower than the preset safety threshold of 100 ppm, confirming that the current state is safe. The system then checks the predicted value for a future period. If the system indicates that maintaining the current storage temperature will cause the peroxide value to exceed the 100 ppm threshold at some point, the system determines that the peroxide generation rate of diethyl ether is too fast under the current environmental conditions. Based on this, the system generates an environmental parameter adjustment command: "Reduce the temperature of the area where A3-2 is located from 22℃ to 16℃ to slow down the peroxide generation rate of diethyl ether," and sends the command to the warehouse management actuator, which then performs the cooling operation through the area air conditioning system. This control process facilitates real-time diagnosis and precise intervention of warehouse risks.

[0025] S3. Obtain the dynamic parameters of the chemical reaction when the target chemical is in the experimental operation stage, compare the dynamic parameters of the chemical reaction with the dynamic risk threshold, generate and issue a second control command to the emergency execution agency based on the comparison result, so as to control the reaction process.

[0026] For example, the test operation phase refers to the period when chemicals are received from the storage area and transferred to the test operation area for weighing, preparation, reaction, and other test activities. After the target chemical is received and transferred to the test operation area, this invention acquires the dynamic chemical reaction parameters of the target chemical during the test operation phase through sensors arranged in the reaction device and test environment. These dynamic chemical reaction parameters are measurement indicators that can reflect the safety status of the chemical reaction process in real time. The dynamic chemical reaction parameters corresponding to different chemicals and different test operations are not fixed but dynamically adapted according to the hazardous characteristics of the chemicals and the specific type of test operation. For reactions involving flammable and explosive substances, the concentration of combustible gas is the core monitoring parameter; for high-pressure reactions, the reaction pressure is the core monitoring parameter; for reactions with violent exothermic reactions, the reaction temperature is the core monitoring parameter; for reactions that may produce toxic gases, the concentration of characteristic gases (such as H2S, CO, NH3, etc.) is the key monitoring parameter. Taking diethyl ether as an example, a researcher retrieved a bottle of diethyl ether from the storage area and transferred it to fume hood No. 2 in the test area for extraction experiments. The reaction device was a constant temperature water bath with a set temperature of 25°C. A combustible gas sensor was installed in the fume hood. Because diethyl ether has flammable and explosive properties, its volatilization and mixing with air may form an explosive atmosphere.

[0027] Therefore, the concentration of combustible gas is a key parameter that needs to be monitored during this experiment. Although the extraction experiment is not a violently exothermic reaction, the heating process still requires temperature monitoring to prevent overheating due to equipment failure. During this experiment, the dynamic parameters of the chemical reaction include the reaction temperature and the concentration of combustible gas in the test area. The system's preset dynamic risk threshold corresponds one-to-one with the dynamic parameters of the chemical reaction: each dynamic parameter has an independent safety threshold, which is set according to the hazardous characteristics of the chemical. By comparing the dynamic parameters of the chemical reaction with the dynamic risk threshold, it is determined whether the current reaction process is in a safe state. If the dynamic parameters of the chemical reaction exceed the dynamic risk threshold, the system automatically generates and issues a second control command to the emergency execution mechanism to perform emergency ventilation or inert gas protection operations to control the risk that is occurring. The emergency execution mechanism refers to the equipment that can receive commands and perform emergency actions, including the emergency ventilation valve of the ventilation system, the inert gas release valve, the reaction heating cut-off device, etc.

[0028] Taking the ether extraction test as an example, the dynamic parameters of the chemical reaction involved in this test include the reaction temperature and the concentration of combustible gas. The corresponding dynamic risk thresholds are as follows: the reaction temperature shall not exceed 35℃, and the concentration of combustible gas shall not exceed 0.34%. During the test, the system will compare the real-time monitored reaction temperature with 35℃ and the real-time monitored combustible gas concentration with 0.34%. If the reaction temperature exceeds 35℃, it indicates that the heating system may be faulty and the heating power supply should be cut off immediately. If the concentration of combustible gas exceeds 0.34%, it indicates that the ether volatilization has reached the warning level and the emergency ventilation should be started immediately.

[0029] S4. Obtain the test record data of the target chemical, and obtain the process influencing factor set based on the test record data and the dynamic parameters of the chemical reaction.

[0030] For example, the present invention monitors the entire experimental operation process to obtain experimental record data. The experimental record data refers to the data recorded by the experimental personnel or automatically collected by the system during the experimental operation, which describes the experimental operation process and the use of materials, including the name, amount, concentration of the chemicals used, experimental steps, and reaction conditions. Key feature information that affects the subsequent stability of chemical waste is extracted from the experimental record data and the dynamic parameters of the chemical reaction, such as whether heavy metal catalysts were used, whether the maximum reaction temperature exceeded the set value, whether abnormal events such as boiling occurred, and whether the reaction pressure fluctuated drastically. The extracted key feature information is matched one by one with a pre-set process influence rule library to obtain the influence weight values ​​of various influence factors. All matched influence factors and their corresponding influence weight values ​​are combined to form a structured process influence factor set.

[0031] Taking the ether extraction test as an example, the test record data shows that the researchers used 500 mL of ether for extraction and added a small amount of potassium iodide as a catalyst; the dynamic parameters of the chemical reaction show that the reaction temperature reached a maximum of 42℃ (set temperature 25℃) during the test, exceeding the set value by 17℃; the concentration of combustible gas was always below the 0.34% threshold and no leakage occurred; however, there was a violent fluctuation in the temperature curve that lasted for about 2 minutes. Key features were extracted from the above data: the use of catalytically active substances, the highest reaction temperature exceeding the set value, and drastic temperature fluctuations. These features were then matched against a pre-defined process influence rule base: Rule R001 "Use of catalyst" triggered, generating a catalyst residue factor with an influence weight of 1; Rule R002 "Highest temperature exceeds the set value by more than 10°C" triggered, generating a thermal shock factor. The influence weight of this factor can be obtained by calculating the ratio of the temperature deviation value to the baseline temperature difference value. The temperature deviation value refers to the difference between the highest temperature monitored during the experiment and the set temperature. The baseline temperature difference value is a saturation threshold set according to the specific characteristics of the chemical, used to normalize the temperature deviation value to an influence weight value between 0 and 1. If the baseline temperature difference value is set to 50°C, the influence weight value of the thermal shock factor is (42-25) / 50=0.34; Rule R003 "Drastic temperature fluctuations" triggered, generating a thermal fluctuation factor with an influence weight of 0.5. All matched influence factors and their influence weight values ​​were then analyzed. A structured set of process influence factors is constructed: {catalyst residue factor: 1, thermal shock factor: 0.34, thermal fluctuation factor: 0.5}. The stability of chemical waste during temporary storage depends not only on its inherent properties but also on its experiences during the experiment, such as the introduction of catalysts, thermal shock, and abnormal reactions. These experiences affect its stability during temporary storage. Without this information, it is impossible to accurately predict its risk during storage. This invention transforms various information that may affect the subsequent stability of chemical waste during the experiment (such as catalyst residue, thermal shock, and abnormal reactions) into structured data that can be directly used for risk assessment in subsequent stages through the process influence factor set. This allows subsequent risk assessments to be calculated based on the actual impact of the experimental process, effectively solving the technical problem in traditional methods where information from different stages is fragmented and risk assessments are independent, preventing risk information from the previous stage from being used as input parameters in subsequent stages.

[0032] S5. Obtain the final test data of chemical waste before the final disposal stage, and perform risk evolution simulation based on the final test data, hazardous characteristic time series data and the process influencing factor set to obtain the temporary storage risk prediction curve of chemical waste. For example, the final disposal stage refers to the period after the experiment is completed, when the remaining chemicals or reaction products are transferred to a designated waste storage area, such as a waste storage cabinet or hazardous waste storage point, for temporary storage and await final compliant disposal. The waste storage cabinet in this invention is an intelligent storage device with active safety disposal function deployed in the laboratory waste storage area. It integrates a variety of sensors and actuators, such as a cooling system, an inert gas injection system, and enhanced ventilation, and is equipped with an independent control system that can receive and execute automated control commands from the risk assessment system. The reason why chemical waste must be stored in the temporary storage area for a period of time and cannot be directly disposed of is that the laboratory itself does not have the final disposal capacity and cannot dump or incinerate chemicals privately. It can only wait for the hazardous waste treatment company to collect and transport them. At the same time, since hazardous waste treatment companies usually have minimum transport volume restrictions, they cannot send vehicles to collect small amounts of chemical waste at a time. Therefore, the laboratory can only adopt a periodic collection mode, which inevitably results in chemical waste being stored in the temporary storage area for several days to several months.

[0033] During the final disposal phase, the chemical reactions of chemical waste are not completely over. For example, acrylate waste liquid may continue to polymerize and release heat at room temperature, and esters and residual moisture may hydrolyze to produce gas. At the same time, the temporary storage environment itself has diurnal temperature differences and air pressure fluctuations, which may cause the container to expand and contract and volatile organic compounds to leak. These risks are not fully manifested the moment the waste is placed in the temporary storage cabinet, but rather evolve dynamically and accumulate gradually during the storage process.

[0034] This invention obtains final detection data reflecting the current physicochemical state of chemical waste through on-site testing methods, including the effective components, pH value, and solid-liquid state of the chemical waste. Through hazardous characteristic time-series data, the actual deterioration process of the target chemical during storage can be clearly defined, i.e., the actual degree of deterioration accumulated by the chemical each day after entering the warehouse due to real environmental stresses (such as temperature fluctuations and humidity changes). This time-series data records the personalized deterioration situation calculated by combining the theoretical deterioration law of the chemical with its actual storage environment. Through the process influencing factor set, it can be identified which factors accelerated or altered subsequent reactions during the experiment, and its function is... The additional effects of the testing process, such as catalyst residue, thermal shock, and thermal fluctuation, are applied to the actual deterioration state of the chemical at the end of the storage phase to obtain the actual deterioration rate that reflects the true situation. At the same time, the final test data reflects the current true state of the chemical waste. Using these three types of data together as the initial conditions of the mechanistic model, the curves of the change of various risk indicators of the chemical waste over time during the future temporary storage period can be calculated according to the pre-set chemical laws. That is, the temporary storage risk prediction curve. The temporary storage risk prediction curve is a curve that describes the evolution trend of the risk indicators of chemical waste over time during the temporary storage period, with time as the horizontal axis and the quantitative value of the risk indicator as the vertical axis.

[0035] This invention integrates risk information generated at three different stages throughout the chemical life cycle into a single predictive model, enabling the risk assessment of temporary storage of chemical waste to be no longer based on a single point of judgment at the present moment, but rather on trend prediction based on complete historical information.

[0036] Taking the ether extraction test as an example, approximately 450 mL of waste liquid was generated after the test, containing ether residue, potassium iodide catalyst, and a small amount of extraction impurities. Before transferring the waste liquid to the waste storage cabinet, on-site testing was conducted to obtain the final test data: pH test strip showed neutrality (pH≈7), the appearance was colorless, transparent, and without precipitation, and the rapid peroxide value test strip showed approximately 50 ppm. The complete deterioration history of the ether during the storage stage was extracted from the hazardous characteristic time series data: the peroxide value was 0 ppm upon entry into the warehouse, and during 75 days of storage, it experienced temperature changes from 18℃ to 22℃, accumulating to 38 ppm at a rate of 0.4-0.65 ppm per day. By fitting the temperature-peroxide value correspondence over these 75 days, and based on the quantitative relationship between temperature and reaction rate in chemistry, the activation energy parameter of the ether was calculated, thus establishing a benchmark model that can be used to predict the deterioration rate of ether at any temperature. For ease of subsequent calculations, the average temperature of 22℃ at the end of the disposal stage was used as the baseline. Based on the reference temperature, the actual degradation rate of diethyl ether at that temperature was calculated. Impact information from the experimental stage was extracted from the process influencing factors set, and the impact weights of all influencing factors were converted into correction factors for the actual degradation rate: the impact weight of catalyst residue was 1, meaning that catalyst residue increased the degradation rate to twice its original value according to preset rules; the impact weight of thermal shock was 0.34, indicating that temperature deviation increased the degradation rate to 1.34 times its original value; and the impact weight of thermal fluctuation was 0.5, increasing the degradation rate to 1.5 times its original value. These three factors are independent and act simultaneously, therefore the total correction factor is the product of the three, i.e., 2 * 1.34 * 1.5 = 4.02, meaning the corrected degradation rate is 4.02 times the actual degradation rate. Using the final detection data as the current prediction starting point, the peroxide value for each day in the future was extrapolated based on the corrected degradation rate, resulting in a temporary storage risk prediction curve for diethyl ether waste liquid during the final disposal stage.

[0037] S6. Determine whether the temporary risk prediction curve meets the preset conditions within the preset observation period: If the preset conditions are met, the chemical waste is determined to be in a stable state within the preset observation period and is allowed to enter the regular disposal process. If the preset conditions are not met, a third control command is generated and issued based on the temporary storage risk prediction curve to drive the waste storage cabinet to perform safe disposal measures.

[0038] For example, the present invention compares the quantified risk index value corresponding to each future prediction time in the temporary storage risk prediction curve with a preset risk threshold. If none of the quantified risk index values ​​exceed the risk threshold during the entire preset observation period, the chemical waste is determined to be in a stable state during this observation period, and the chemical waste is allowed to continue to be stored in the temporary storage cabinet in a normal manner. If the quantified risk index value at any prediction time exceeds the risk threshold, a corresponding third control command is generated and issued to the waste temporary storage cabinet according to the specific indicators exceeding the risk threshold in the risk prediction curve and their severity, driving it to perform targeted safety disposal measures, such as initiating cooling, opening depressurization, spraying neutralization, or transferring high-risk chemical waste to an isolation chamber. Through the above operations, a control closed loop from risk assessment to precise proactive intervention can be achieved in the waste disposal stage based on forward-looking risk prediction.

[0039] In one embodiment, step S1, which involves performing storage incompatibility analysis and environmental stress degradation analysis based on the storage data to obtain a storage incompatibility risk map and hazardous characteristic time-series data, includes: S11. Obtain chemical ledger data and storage environment data based on the storage data. The chemical ledger data includes the identification information, hazard attributes and storage location coordinates of all currently stored chemicals. Based on the storage environment data and the chemical ledger data, perform environmental stress degradation analysis to obtain hazardous characteristic time series data. For example, by acquiring identification information, the present invention can uniquely identify each chemical, facilitating subsequent association with its storage requirements and degradation kinetic parameters from other data sources; acquiring hazard attributes enables risk calculation based on the incompatibilities between chemicals in subsequent storage incompatibility analysis; acquiring storage location coordinates allows mapping chemicals to a spatial grid, achieving precise risk location and visualization.

[0040] S12. Map the storage location coordinates of all the currently stocked chemicals to a two-dimensional spatial grid to obtain a warehouse location grid map; For example, this invention maps the storage location coordinates of chemicals to a cell in a two-dimensional spatial grid, where the horizontal axis represents the shelf number and the vertical axis represents the shelf layer number. Each grid cell corresponds to a specific physical storage location, such as A3-2 representing the second location on the third layer of shelf A. Simultaneously, the chemical identification information and hazard attributes stored at that location are associated with the grid cell, forming a location-chemical mapping relationship. This generates a warehouse location grid map that perfectly corresponds to the actual shelf layout of the warehouse area. Each cell in this grid map contains not only its spatial coordinate information but also information about the chemicals stored at that location, including the chemical name and hazard attributes. This grid map serves as the spatial carrier for subsequent risk calculations, enabling the precise location and visualization of the chemicals stored at each location and their risk status, providing a basic data framework for identifying high-risk areas and specific risk sources.

[0041] S13. Obtain the storage incompatibility rule base, and according to the hazard attribute of each chemical, query other hazard attributes that have a prohibitive relationship with the hazard attribute in the storage incompatibility rule base to obtain multiple chemical prohibition combinations and corresponding risk weight coefficients; For example, this invention acquires a storage incompatibility rule base, which is a mapping table based on chemical safety knowledge. This base defines the incompatibilities between different hazard categories and their corresponding risk weight coefficients. For instance, "flammable liquids" and "oxidizers" are incompatible for storage, with a risk weight coefficient of 8, indicating that contact could cause a fire or explosion with serious consequences. For all currently stocked chemicals, the invention queries the storage incompatibility rule base based on their hazard attributes, filters out all chemical incompatibilities that exist, and obtains the risk weight coefficient corresponding to each pair of chemical incompatibilities. Through this query and matching process, chemical incompatibilities knowledge is transformed into structured data that can be computed by a computer.

[0042] S14. Traverse each pair of incompatible chemical combinations in the warehouse location grid diagram, and obtain the spatial proximity coefficient of each pair of incompatible chemical combinations based on the storage location coordinates. For example, the present invention uses " "Calculate the spatial proximity coefficient, where s represents the spatial proximity coefficient, (x1, y1) represents the storage location coordinates of the first chemical in the incompatible chemical combination, (x2, y2) represents the storage location coordinates of the second chemical in the incompatible chemical combination, and α represents the attenuation factor, which is set according to the actual layout and safety requirements of the storage area, such as a value of 0.8; the formula for calculating the spatial proximity coefficient is based on the physical law that risk decreases exponentially with spatial distance: the closer the spatial distance between two incompatible chemicals, the higher the probability of contact between them in the event of a leak or splash, and therefore the greater the risk contribution. As the distance increases, the probability of contact decreases exponentially, rather than linearly." The symbol "" represents the Euclidean distance between the two. Since a storage cell grid stores only one type of chemical, incompatible combinations only exist between different storage cells. Therefore, the Euclidean distance is greater than or equal to "1". When the Euclidean distance is equal to "1", the spatial proximity coefficient is equal to "1", indicating that the risk is completely transmitted. When the Euclidean distance is greater than "1", the spatial proximity coefficient decreases rapidly with the increase of the Euclidean distance, indicating that as the spatial distance increases, the possibility of the two coming into contact and causing an accident gradually decreases.

[0043] S15. Obtain the dynamic incompatibility risk score corresponding to each cell in the storage location grid diagram according to the risk weight coefficient and the spatial proximity coefficient, and fill the dynamic incompatibility risk score into the corresponding cell of the storage location grid diagram to generate a storage incompatibility risk map. For example, this invention calculates the product of the risk weight coefficient and the spatial proximity coefficient corresponding to each pair of incompatible chemical combinations to obtain the local risk contribution value of the storage cell containing that pair of incompatible chemical combinations. For each storage cell in the storage location grid diagram, all its corresponding local risk contribution values ​​are summed to obtain the dynamic incompatibility risk score corresponding to that cell. All calculated risk scores are filled into the corresponding cells of the storage location grid diagram to generate a storage incompatibility risk map. This map is presented in the form of a two-dimensional grid, and the value of each cell intuitively reflects the degree of risk faced by the storage location due to the incompatibility relationship between the stored chemicals and the chemicals in adjacent locations. Through this map, the system can quickly locate high-risk areas and specific risk sources, such as which incompatible substances are placed together, thereby providing accurate decision-making basis for classified and isolated storage and realizing the transformation from passive response to proactive prevention.

[0044] In one embodiment, step S11, which involves performing environmental stress degradation analysis based on the storage environment data and the chemical ledger data to obtain time-series data of hazardous characteristics, includes: S111. Obtain a basic chemical information database, and obtain the storage requirements and baseline degradation rate of the target chemical based on the basic chemical information database; For example, this invention accesses a pre-built chemical basic information database, which stores the inherent property data of each chemical, including storage requirements such as recommended storage temperature range, light protection requirements, and moisture protection requirements, as well as a baseline degradation rate to describe the rate of degradation. The baseline degradation rate refers to a parameter that can quantitatively describe the mathematical relationship between environmental stress and degradation rate. Specifically, it includes: the baseline degradation rate of the chemical at a reference temperature (e.g., 20°C), for example, diethyl ether generates 0.5 ppm of peroxide per day at 20°C; the activation energy parameter or temperature coefficient of the reaction rate as a function of temperature, i.e., the factor by which the degradation rate increases for every 10°C increase in temperature, typically 2 to 3 times; for humidity-sensitive chemicals, the humidity effect coefficient, i.e., the factor by which the degradation rate increases for every certain percentage increase in humidity; and for photosensitive chemicals, the light intensity effect coefficient, i.e., the factor by which the degradation rate increases for every certain increase in light intensity. By obtaining this basic information, accurate chemical property basis can be provided for subsequent degradation calculations.

[0045] S112. Obtain the key environmental stresses that need to be monitored during the storage of the target chemical according to the storage requirements, and extract the historical environmental parameter sequence corresponding to the key environmental stresses from the storage environment data. For example, this invention determines the types of critical environmental stresses that need to be monitored during the storage of a target chemical based on its storage requirements. For temperature-sensitive chemicals, such as diethyl ether and nitrocellulose, the critical environmental stress is temperature; for humidity-sensitive chemicals, such as metallic sodium and acyl chloride, the critical environmental stress is humidity; and for photosensitive chemicals, such as hydrogen peroxide, the critical environmental stress is light intensity. After determining the types of critical environmental stresses, a sequence of historical environmental parameters corresponding to the storage location of the chemical is extracted from the warehousing environment data. This sequence consists of continuously recorded environmental parameter values, such as daily average temperature and daily average humidity, according to timestamps. The purpose of extracting the historical environmental parameter sequence is to provide real environmental input data for subsequent daily degradation calculations, so that the calculation results can reflect the impact of actual storage conditions.

[0046] S113. Extract the entry time of the target chemical from the chemical ledger data, and calculate the quantitative value of the hazard index of the target chemical during storage due to the action of key environmental stress based on the historical environmental parameter sequence, entry time and the baseline deterioration rate. For example, this invention determines the starting point for deterioration calculation by extracting the chemical's warehousing time from chemical ledger data; using the warehousing time as the starting point, and the daily average environmental parameter value in the historical environmental parameter sequence as the daily environmental stress input, combined with the baseline deterioration rate, the cumulative increase in hazardous indicators of the chemical during storage is calculated daily; taking the daily generation of 0.5 ppm peroxide by diethyl ether as an example, through " "Calculate the peroxide increment, where R" i R0 represents the increment of peroxide generated on day i, Q represents the baseline degradation rate, and T represents the temperature coefficient. i T represents the average storage temperature on day i, T0 represents the recommended storage temperature, and T... a The formula represents the temperature deviation baseline value, and i represents the storage day number. This formula is based on the exponential relationship between temperature and reaction rate described by the Arrhenius equation. In chemical reaction kinetics, the effect of temperature on reaction rate follows the Arrhenius equation, which shows that the reaction rate constant increases exponentially with increasing temperature. This invention uses the temperature coefficient approximation method to describe the accelerating or decelerating effect of temperature changes on the degradation rate through an exponential function. That is, when the average storage temperature on day i is equal to the recommended storage temperature, the exponential term is 0, and the peroxide increment is equal to the amount generated corresponding to the baseline degradation rate. When the average storage temperature is higher than the recommended storage temperature, the exponential term is positive, indicating that the temperature increase accelerates the generation of peroxides. The peroxide increment calculated each day is accumulated to obtain the cumulative peroxide value at the end of each day, thereby obtaining complete time-series data on the change of peroxide value of diethyl ether over time during storage. Through this daily accumulation calculation method, all environmental processes such as temperature fluctuations and humidity changes experienced by chemicals during storage are quantified into the change trajectory of hazard indicators.

[0047] S114. Arrange the quantified values ​​of the hazard indicators in chronological order to obtain the time series data of the hazard characteristics; For example, the present invention calculates the hazard index quantification values ​​at the end of each day's storage and arranges them in chronological order to form a data sequence with time as the independent variable and the hazard index quantification values ​​as the dependent variable, namely, hazard characteristic time series data; the time series data completely records the evolution of the hazardous state of the chemical from its entry into the warehouse to the present moment, for example, the complete data of the peroxide value of diethyl ether gradually accumulating from 0 ppm to 38 ppm.

[0048] In one embodiment, step S4, which involves obtaining the set of process influencing factors based on the experimental record data and the dynamic parameters of the chemical reaction, includes: S41. Obtain the process influence rule base and extract the first key feature information from the test record data; For example, this invention pre-constructs a process influence rule base, which is a mapping table based on chemical safety knowledge and historical experimental data. This base defines the correspondence between various experimental characteristic information and influence factors, as well as the assignment rules for influence weight values. This invention extracts first key characteristic information from experimental record data. This first key characteristic information refers to qualitative event information that can be judged by "yes or no," including whether catalytically active substances were used, whether abnormal events such as boiling occurred, etc. Its characteristic is that whether it occurs determines the existence of the corresponding influence factor; therefore, binary assignment can accurately characterize it. By extracting qualitative events separately, key operational information in the experiment can be incorporated into the risk assessment system in the simplest and most effective way.

[0049] S42. Based on the first key feature information, perform a matching query in the process influence rule base to obtain multiple first influence factors and their corresponding first influence weight values; For example, the present invention uses the extracted first key feature information as a query condition and matches it one by one in the process influence rule base. The rule base pre-stores the correspondence between feature information and influence factors. For example, when the feature information "use of catalyst" is "yes", the catalyst residue factor is matched, and its influence weight value is assigned to 1 according to the rule, indicating its existence; when the feature information "boiling occurred" is "yes", the abnormal event factor is matched, and its influence weight value is assigned to 1 according to the rule. Through this matching query, the qualitative events in the experimental records are transformed into structured first influence factors and their first influence weight values, so that the subjectively recorded data can be automatically identified and quantified by the computer system.

[0050] S43. Extract second key feature information from the experimental record data and the dynamic parameters of the chemical reaction, and perform matching query in the process influence rule base based on the second key feature information to obtain the weight mapping rules of multiple second influence factors; For example, this invention extracts second key feature information from experimental record data and dynamic parameters of chemical reactions. This second key feature information refers to quantitative parameter information that can be described by specific numerical values, including the difference between the highest reaction temperature and the set temperature, temperature fluctuation amplitude, pressure fluctuation amplitude, etc. These features belong to quantitative event information, characterized by their influence continuously changing with the magnitude of the parameter values. By extracting quantitative parameters separately, a refined quantification of the impact on the experimental process can be achieved. This invention uses the extracted second key feature information as a query condition to match the corresponding weight mapping rule in the process influence rule base. This mapping rule defines the functional relationship between specific numerical values ​​and influence weight values. Obtaining the weight mapping rule can provide a calculation basis for subsequent quantitative calculations.

[0051] S44. Obtain multiple second influencing factors and their corresponding second influencing weight values ​​according to the second key feature information and the weight mapping rule, and encapsulate all the first influencing factors and their corresponding first influencing weight values ​​and all the second influencing factors and their corresponding second influencing weight values ​​into a process influencing factor set. For example, the present invention calculates the weighting by substituting the specific numerical values ​​of the second key feature information into the matched weighting mapping rule. Taking a nitration reaction experiment as an example, the weighting mapping rule for the thermal shock factor corresponding to this reaction is as follows: Where ω represents the influence weight of the thermal shock factor, ΔT represents the temperature deviation value, and T base This formula represents the reaction set temperature. It uses relative temperature deviation as the core measure of thermal shock intensity, reflecting the severity of the deviation relative to the reaction temperature level through the ratio of the absolute value of the temperature deviation to the absolute value of the reaction set temperature. A positive constant is introduced into the denominator to avoid calculation invalidity when the reaction set temperature is 0 or negative, ensuring the formula is applicable to various temperature conditions. Finally, the minimum value of this ratio and 1 is used to achieve weight normalization constraints, ensuring the influence weight of the thermal shock factor is always limited to a reasonable range of 0 to 1. This aligns with the physical law that the degree of thermal shock increases with the relative deviation, and also meets the requirements of standardized weight values ​​and stable, reliable calculation. If the nitration reaction experiment data is extracted from the experimental records and dynamic parameters of the chemical reaction... During the process, the temperature deviation was 25℃, and the reaction set temperature was 50℃. Substituting the data into the weighting mapping rule of the thermal shock factor, the influence weight value of the thermal shock factor was calculated to be 0.5. Then, the first influence factor and its corresponding first influence weight value were combined with the second influence factor and its corresponding second influence weight value and encapsulated into a structured process influence factor set. This process influence factor set transforms various information that may affect the subsequent stability of chemical waste during the experiment into structured data that can be directly used in subsequent stages. This allows subsequent risk assessments to be calculated based on the actual impact of the experiment, thereby helping to solve the technical problem in traditional methods where risk information from previous stages cannot be transmitted to subsequent stages due to the fragmentation of information at each stage.

[0052] In one embodiment, step S5, which involves performing risk evolution simulation based on the final detection data, hazardous characteristic time-series data, and the process influencing factor set to obtain the temporary storage risk prediction curve for chemical waste, includes: S51. Obtain the current hazard index quantification value of the chemical waste based on the final detection data, and obtain the actual deterioration rate of the target chemical at the end of the storage stage based on the hazard characteristic time series data. For example, the present invention obtains the current hazard index quantification value of chemical waste from the final detection data, which serves as the starting point for subsequent predictions; and reads the hazard index quantification value of the last continuous period (such as the last 7 days) in the time series data of hazardous characteristics, and calculates the average increase per unit time during that period. For example, if the peroxide value of diethyl ether increases by 0.65 ppm per day during the last 7 days of storage, then the actual deterioration rate is 0.65 ppm / day. This rate reflects the speed of deterioration of the chemical after experiencing a real storage environment and is the basis for subsequent corrections.

[0053] S52. Based on the set of process influencing factors, the actual degradation rate is corrected to obtain the corrected degradation rate. For example, the present invention extracts each influencing factor and its corresponding influence weight value from the process influencing factor set. For the catalyst residue factor, according to the principle of catalytic kinetics, the catalyst increases the reaction rate by reducing the reaction activation energy. Its catalytic reaction rate is directly proportional to the catalyst concentration. Since the specific amount of catalyst is usually not recorded in the test records, the present invention determines the correction factor of the catalyst residue factor based on the experimental calibration results of the combination of the catalyst and chemical waste. For example, if the calibration results show that the degradation rate increases to twice the original when there is catalyst residue, then the influence weight value 1 of the catalyst residue factor is mapped to the calibration factor.

[0054] For the thermal shock factor, according to the Arrhenius equation, the effect of temperature change on the reaction rate is determined by the activation energy. According to the linear approximation of the Arrhenius equation, when the temperature change is small, the reaction rate factor is approximately linearly related to the degree of temperature deviation. Therefore, the influence weight value corresponding to the thermal shock factor is used as the increment of the rate factor, that is, the rate factor is 1 + 0.34 = 1.34. For the thermal fluctuation factor, according to the non-equilibrium thermodynamics theory, after the system experiences temperature fluctuations, its molecular energy level distribution deviates from the equilibrium state, and the degree of increase in reaction rate is positively correlated with the fluctuation amplitude. The thermal fluctuation factor is a weight value determined according to the fluctuation amplitude and a preset classification rule. The rate correction factor corresponding to this weight value is obtained in the following way: for a specific chemical, the deterioration rate of chemical waste after experiencing temperature fluctuations of different amplitudes is measured in advance through experiments, and a mapping relationship between fluctuation amplitude and rate factor is established. For example, the rate factor is 1.5 when the fluctuation amplitude is severe, 1.2 when it is moderate, and 1.1 when it is slight. The three influencing factors are independent of each other and act simultaneously. According to the multi-factor coupling principle in chemical kinetics, the overall reaction rate constant is the product of the rate constants of each independent factor. Therefore, multiplying the correction factors together gives a comprehensive correction factor of 2*1.34*1.5=4.02. Then, multiplying the actual degradation rate of 0.65ppm / day by the comprehensive correction factor of 4.02 gives a corrected degradation rate of approximately 2.61ppm / day. Through this correction based on physicochemical principles, the additional effects generated during the experiment (catalyst residue, thermal shock, and thermal fluctuations) are transformed into a scientifically based degradation rate amplification factor, enabling subsequent predictions to objectively reflect the true impact of the experiment on the stability of chemical waste.

[0055] S53. Based on the corrected degradation rate and the current hazard index quantification value, the hazard index is accumulated and extrapolated to obtain the predicted hazard index quantification value for each future prediction time. For example, this invention uses the current hazard indicator quantification value of 50 ppm as the prediction starting point, and the corrected deterioration rate of 2.61 ppm / day as the increase per unit time. It accumulates the values ​​stepwise according to a preset time step (e.g., daily). That is, the predicted value for the first day is 50 + 2.61 = 52.61 ppm, the predicted value for the second day is 52.61 + 2.61 = 55.22 ppm, and so on, until the preset prediction period (e.g., 7 days or 30 days), to obtain the predicted hazard indicator quantification value for each future day. Through this cumulative extrapolation, the three types of information—warehouse history, test impact, and current status—are integrated into a quantitative prediction of future hazard indicator changes.

[0056] S54. Perform risk quantification mapping on the predicted risk index quantification value to obtain the risk index quantification value at each prediction time in the future, and construct a temporary risk prediction curve with prediction time as the horizontal axis and risk index quantification value as the vertical axis. For example, this invention compares the predicted hazard index quantification value at each prediction time with a preset safety threshold, calculates the ratio of the predicted hazard index quantification value to the preset safety threshold, and obtains the risk index quantification value. For example, if the safety threshold for the peroxide value of ether waste liquid is set to 100 ppm, then the risk index quantification value on day 1 is 52.61 / 100 = 0.5261, and on day 2 it is 55.22 / 100 = 0.5522. When the predicted value reaches 100 ppm, the risk index quantification value is 1; when it exceeds 100 ppm, it is greater than 1. All the calculated risk index quantification values ​​are arranged in chronological order, and a temporary storage risk prediction curve is plotted with the prediction time as the horizontal axis and the risk index quantification value as the vertical axis. This curve intuitively reflects the evolution trend of the risk of chemical waste during temporary storage over time—when the curve is below 1, it indicates that the risk is controllable; when the curve is close to or exceeds 1, it indicates that the chemical waste is about to enter a dangerous state. Through this curve, early warning can be given before the risk occurs, providing a quantitative decision-making basis for taking intervention measures such as cooling, isolation, and priority disposal, realizing the transformation from passive response to active prevention.

[0057] In one embodiment, step S6, which generates and issues a third control command based on the temporary risk prediction curve, includes: S61. Obtain a preset risk threshold, and extract the risk over-limit prediction period and the corresponding risk index quantification value from the temporary risk prediction curve that exceeds the preset risk threshold. For example, the present invention identifies all time points exceeding a preset risk threshold by iterating through the risk index quantification values ​​at each prediction time, divides these consecutive time points into risk over-limit prediction periods, and records the risk index quantification values ​​corresponding to each time point within the period. By extracting the risk over-limit prediction periods, it is possible to clearly identify when chemical waste will enter a dangerous state, providing a time basis for the timing planning of subsequent control instructions, enabling safe disposal measures to be accurately executed before the risk occurs or when the risk first appears, avoiding premature intervention that leads to resource waste or premature intervention that leads to accidents.

[0058] S62. Determine the risk indicator type based on the quantified value of the risk indicator, and obtain the degree of risk exceeding the standard based on the quantified value of the risk indicator and the preset risk threshold; For example, this invention determines the category of current risk based on the risk indicator type corresponding to the quantified risk indicator value, such as pressure, temperature, or gas concentration. Simultaneously, it calculates the difference between the quantified risk indicator value and a preset risk threshold, and then calculates the ratio of this difference to the preset risk threshold as the degree of risk exceeding the limit. For instance, when the quantified risk indicator value is 1.5 and the risk threshold is 1, the degree of exceeding the limit is 50%. By determining the risk indicator type and the degree of exceeding the limit, the type and severity of risk can be accurately identified, providing precise input for subsequent matching of targeted safety measures, making the generation of control commands more scientific and reasonable.

[0059] S63. Obtain the safety handling rule base, and perform a query and match in the safety handling rule base based on the risk indicator type and the degree of risk exceeding the standard to obtain the basic control action; For example, this invention obtains a pre-set safety handling rule base, which stores the correspondence between different risk indicator types and their exceedance levels and basic control actions. For instance, the rule base defines: when the risk indicator type is pressure and the exceedance level is within the mild range, the basic control action of "opening the pressure relief valve" is matched; when the risk indicator type is temperature and the exceedance level is within the severe range, the combined actions of "starting the cooling system" and "transferring to the isolation chamber" are matched; when the risk indicator type is gas concentration, the basic control actions of "starting emergency ventilation" or "spray neutralization" are matched. By using the risk indicator type and the degree of risk exceedance as query conditions, the corresponding basic control actions are matched in the rule base, so that the risk identification results can be directly converted into an executable control scheme, realizing the automated mapping from risk assessment to control decision.

[0060] S64. Based on the risk over-limit prediction period and the basic control action, a multi-actuator control sequence is obtained, and a third control instruction is generated by encoding the multi-actuator control sequence. For example, the present invention determines the timing of control actions based on the extracted risk exceeding the limit prediction period: for the upcoming risk exceeding the limit period, preventive control actions are planned to be executed in advance before the risk occurs, such as starting the cooling system 2 hours before the predicted exceedance; for the risk exceeding the limit period that has already occurred or lasts for a long time, emergency control actions are planned to be executed immediately; at the same time, based on the basic control actions and combined with the physical capability parameters of each actuator of the waste storage cabinet, a single basic control action is decomposed into a detailed control sequence executed by multiple actuators in chronological order; then the planned multi-actuator control sequence is encoded according to the communication protocol of the waste storage cabinet control system to generate a third control instruction that can be parsed and executed by the system; through this planning and encoding process, the risk prediction result is transformed into specific, orderly, and executable control instructions, realizing a control closed loop from risk assessment to precise proactive intervention, enabling the storage cabinet to automatically execute forward-looking safety disposal measures without human intervention.

[0061] This application also provides a risk assessment system for the entire life cycle of laboratory chemicals, including: The storage analysis module is used to acquire storage data of the target chemical when it is in the storage stage, and to perform storage incompatibility analysis and environmental stress degradation analysis based on the storage data to obtain storage incompatibility risk map and hazardous characteristic time series data. The warehouse control module is used to generate and issue a first control command to the warehouse management actuator based on the storage incompatibility risk map and the time series data of the hazardous characteristics, so as to perform preventive adjustment of classified and isolated storage and environmental parameters; The test monitoring module is used to acquire the dynamic parameters of the chemical reaction when the target chemical is in the test operation stage, compare the dynamic parameters of the chemical reaction with the dynamic risk threshold, generate and issue a second control command to the emergency execution agency based on the comparison result, so as to control the reaction process; The process quantification module is used to acquire test record data of the target chemical and obtain a set of process influencing factors based on the test record data and the dynamic parameters of the chemical reaction; The risk simulation module is used to obtain the final detection data of chemical waste before the final disposal stage, and to perform risk evolution simulation based on the final detection data, the time series data of hazardous characteristics and the set of process influencing factors to obtain the temporary storage risk prediction curve of chemical waste. The processing execution module is used to determine whether the temporary risk prediction curve meets preset conditions within a preset observation period: If the preset conditions are met, the chemical waste is determined to be in a stable state within the preset observation period and is allowed to enter the regular disposal process. If the preset conditions are not met, a third control command is generated and issued based on the temporary storage risk prediction curve to drive the waste storage cabinet to perform safe disposal measures.

[0062] In one embodiment, the risk simulation module includes: The data acquisition module is used to acquire the current hazard index quantification value of the chemical waste based on the final detection data, and to acquire the actual deterioration rate of the target chemical at the end of the storage stage based on the hazard characteristic time series data. The degradation correction module is used to correct the actual degradation rate based on the process influencing factor set to obtain the corrected degradation rate. The cumulative extrapolation module is used to perform cumulative extrapolation of the risk index based on the corrected degradation rate and the current risk index quantification value, so as to obtain the predicted risk index quantification value at each prediction time in the future. The curve construction module is used to perform risk quantification mapping on the predicted risk index quantification value to obtain the risk index quantification value at each prediction time in the future, and construct a temporary risk prediction curve with prediction time as the horizontal axis and risk index quantification value as the vertical axis.

[0063] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described risk assessment method for the entire life cycle of laboratory chemicals.

[0064] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described risk assessment method for the entire life cycle of laboratory chemicals.

[0065] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in this application and in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0066] 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, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0067] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for risk assessment of the entire life cycle of laboratory chemicals, characterized in that, include: Acquire storage data of the target chemical when it is in the storage stage, and perform storage incompatibility analysis and environmental stress degradation analysis based on the storage data to obtain storage incompatibility risk map and time series data of hazardous characteristics; Based on the storage incompatibility risk map and the time series data of the hazardous characteristics, a first control command is generated and issued to the warehouse management actuator to perform preventive adjustments to the classification and isolation storage and environmental parameters; The dynamic parameters of the chemical reaction of the target chemical are obtained when it is in the experimental operation stage, and the dynamic parameters of the chemical reaction are compared with the dynamic risk threshold. Based on the comparison result, a second control command is generated and issued to the emergency execution agency to control the reaction process. Obtain test record data of the target chemical, and obtain a set of process influencing factors based on the test record data and the dynamic parameters of the chemical reaction; Obtain the final test data of chemical waste before the final disposal stage, and perform risk evolution simulation based on the final test data, hazardous characteristic time series data and the process influencing factor set to obtain the temporary storage risk prediction curve of chemical waste; Determine whether the temporary risk prediction curve meets the preset conditions within the preset observation period: If the preset conditions are met, the chemical waste is determined to be in a stable state within the preset observation period and is allowed to enter the regular disposal process. If the preset conditions are not met, a third control command is generated and issued based on the temporary storage risk prediction curve to drive the waste storage cabinet to perform safe disposal measures.

2. The risk assessment method for the entire life cycle of laboratory chemicals according to claim 1, characterized in that, The steps of performing storage incompatibility analysis and environmental stress degradation analysis based on the storage data to obtain a storage incompatibility risk map and time-series data of hazardous characteristics include: Based on the warehousing data, chemical ledger data and warehousing environment data are obtained. The chemical ledger data includes the identification information, hazard attributes and storage location coordinates of all currently stocked chemicals. Based on the warehousing environment data and the chemical ledger data, environmental stress degradation analysis is performed to obtain time-series data of hazardous characteristics. Map the storage location coordinates of all the currently stocked chemicals to a two-dimensional spatial grid to obtain a warehouse location grid map; Obtain the storage incompatibility rule base, and query other hazard attributes that have a prohibitive relationship with the hazard attribute in the storage incompatibility rule base according to the hazard attribute of each chemical, to obtain multiple chemical prohibition combinations and corresponding risk weight coefficients; Traverse each pair of incompatible chemical combinations in the warehouse location grid diagram, and obtain the spatial proximity coefficient of each pair of incompatible chemical combinations based on the storage location coordinates; The dynamic incompatibility risk score corresponding to each cell in the storage location grid is obtained based on the risk weight coefficient and the spatial proximity coefficient, and the dynamic incompatibility risk score is filled into the corresponding cell of the storage location grid to generate a storage incompatibility risk map.

3. The risk assessment method for the entire life cycle of laboratory chemicals according to claim 2, characterized in that, The step of performing environmental stress degradation analysis based on the storage environment data and the chemical ledger data to obtain time-series data of hazardous characteristics includes: Obtain a basic chemical information database, and based on the basic chemical information database, obtain the storage requirements and baseline degradation rate of the target chemical. Based on the storage requirements, the key environmental stresses that need to be monitored during the storage of the target chemical are obtained, and the historical environmental parameter sequence corresponding to the key environmental stresses is extracted from the storage environment data. Extract the entry time of the target chemical from the chemical ledger data, and calculate the quantitative value of the hazard index of the target chemical during storage due to the effects of key environmental stresses based on the historical environmental parameter sequence, entry time, and baseline deterioration rate. The quantified values ​​of the hazard indicators are arranged in chronological order to obtain time-series data of hazard characteristics.

4. The risk assessment method for the entire life cycle of laboratory chemicals according to claim 1, characterized in that, The step of obtaining the process influencing factor set based on the experimental record data and the dynamic parameters of the chemical reaction includes: The process influences the rule base, and the first key feature information is extracted from the test record data; Based on the first key feature information, a matching query is performed in the process influence rule base to obtain multiple first influence factors and their corresponding first influence weight values; The second key feature information is extracted from the experimental record data and the dynamic parameters of the chemical reaction. Based on the second key feature information, a matching query is performed in the process influence rule base to obtain the weight mapping rules of multiple second influence factors. Based on the second key feature information and the weight mapping rule, multiple second influence factors and their corresponding second influence weight values ​​are obtained, and all the first influence factors and their corresponding first influence weight values, as well as all the second influence factors and their corresponding second influence weight values, are encapsulated into a process influence factor set.

5. The risk assessment method for the entire life cycle of laboratory chemicals according to claim 1, characterized in that, The step of performing risk evolution simulation based on the final detection data, hazardous characteristic time series data, and the process influencing factor set to obtain the temporary storage risk prediction curve of chemical waste includes: The current hazard index quantification value of the chemical waste is obtained based on the final detection data, and the actual deterioration rate of the target chemical at the end of the storage stage is obtained based on the time series data of the hazardous characteristics. The actual degradation rate is corrected based on the set of process influencing factors to obtain the corrected degradation rate; Based on the corrected degradation rate and the current hazard index quantification value, the hazard index is accumulated and extrapolated to obtain the predicted hazard index quantification value for each future prediction time. The predicted risk index quantification value is mapped to risk quantification to obtain the risk index quantification value at each prediction time in the future, and a temporary risk prediction curve is constructed with prediction time as the horizontal axis and risk index quantification value as the vertical axis.

6. The risk assessment method for the entire life cycle of laboratory chemicals according to claim 1, characterized in that, The step of generating and issuing a third control command based on the temporary risk prediction curve includes: Obtain a preset risk threshold, and extract the risk over-limit prediction period and the corresponding risk indicator quantification value from the temporary risk prediction curve that exceeds the preset risk threshold. The risk indicator type is determined based on the quantified value of the risk indicator, and the degree of risk exceeding the standard is obtained based on the quantified value of the risk indicator and the preset risk threshold. Obtain the safety handling rule base, and perform a query and match in the safety handling rule base based on the risk indicator type and the degree of risk exceeding the standard to obtain the basic control action; Based on the predicted risk overshoot period and the basic control actions, a multi-actuator control sequence is obtained, and a third control instruction is generated by encoding the multi-actuator control sequence.

7. A risk assessment system for the entire life cycle of laboratory chemicals, characterized in that, include: The storage analysis module is used to acquire storage data of the target chemical when it is in the storage stage, and to perform storage incompatibility analysis and environmental stress degradation analysis based on the storage data to obtain storage incompatibility risk map and hazardous characteristic time series data. The warehouse control module is used to generate and issue a first control command to the warehouse management actuator based on the storage incompatibility risk map and the time series data of the hazardous characteristics, so as to perform preventive adjustment of classified and isolated storage and environmental parameters; The test monitoring module is used to acquire the dynamic parameters of the chemical reaction when the target chemical is in the test operation stage, compare the dynamic parameters of the chemical reaction with the dynamic risk threshold, generate and issue a second control command to the emergency execution agency based on the comparison result, so as to control the reaction process; The process quantification module is used to acquire test record data of the target chemical and obtain a set of process influencing factors based on the test record data and the dynamic parameters of the chemical reaction; The risk simulation module is used to obtain the final detection data of chemical waste before the final disposal stage, and to perform risk evolution simulation based on the final detection data, the time series data of hazardous characteristics and the set of process influencing factors to obtain the temporary storage risk prediction curve of chemical waste. The processing execution module is used to determine whether the temporary risk prediction curve meets preset conditions within a preset observation period: If the preset conditions are met, the chemical waste is determined to be in a stable state within the preset observation period and is allowed to enter the regular disposal process. If the preset conditions are not met, a third control command is generated and issued based on the temporary storage risk prediction curve to drive the waste storage cabinet to perform safe disposal measures.

8. A risk assessment system for the entire life cycle of laboratory chemicals according to claim 7, characterized in that, The risk simulation module includes: The data acquisition module is used to acquire the current hazard index quantification value of the chemical waste based on the final detection data, and to acquire the actual deterioration rate of the target chemical at the end of the storage stage based on the hazard characteristic time series data. The degradation correction module is used to correct the actual degradation rate based on the process influencing factor set to obtain the corrected degradation rate. The cumulative extrapolation module is used to perform cumulative extrapolation of the risk index based on the corrected degradation rate and the current risk index quantification value, so as to obtain the predicted risk index quantification value at each prediction time in the future. The curve construction module is used to perform risk quantification mapping on the predicted risk index quantification value to obtain the risk index quantification value at each prediction time in the future, and construct a temporary risk prediction curve with prediction time as the horizontal axis and risk index quantification value as the vertical axis.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images