Chemical storage logistics safety monitoring management control system based on internet of things

Abstract

The application relates to the technical field of chemical warehouse management, in particular to a chemical warehouse logistics safety monitoring management control system based on the Internet of Things, which comprises an acquisition module, an analysis module and a control module; the acquisition module is used for acquiring monitoring values corresponding to sensors in integrated monitoring instruments; the analysis module is used for determining local saliencies of the monitoring values corresponding to the sensors at different collection time points based on the monitoring values corresponding to the sensors; effective variation factors of the monitoring values corresponding to the sensors at the different collection time points are acquired according to the local saliencies of the monitoring values corresponding to the sensors at the different collection time points; the effective variation factors of the monitoring values corresponding to the sensors at the different collection time points are used to determine environmental abnormality degrees of the integrated monitoring instruments at a current time point; and the control module is used for managing and controlling the chemical warehouse logistics according to the environmental abnormality degrees of the integrated monitoring instruments at the current time point. The application can improve the real-time performance of chemical warehouse logistics monitoring and the judgment sensitivity in the initial stage of abnormality.

Description

Technical Field

[0001] This invention relates to the field of chemical storage management technology, and more specifically to a chemical storage logistics safety monitoring, management and control system based on the Internet of Things. Background Technology

[0002] The chemical warehousing and logistics management system collects real-time safety status data of the environment, equipment, goods, and personnel through various intelligent sensors and controllers deployed in chemical warehouses, transport vehicles, and key nodes. This data is transmitted to the cloud platform via IoT gateways and networks, where it is processed, alerted, and used for intelligent decision-making through big data analysis and artificial intelligence algorithms. Ultimately, it enables intelligent perception, precise control, and efficient management of the entire chemical warehousing and logistics process through a visualization platform and mobile terminals.

[0003] Because hazardous chemicals are stored, existing chemical storage and logistics management systems first deploy monitoring equipment in different storage locations, and then set uniform, fixed environmental parameter thresholds (such as upper temperature limits) for all monitoring equipment. When the monitoring data exceeds the set environmental parameter thresholds, the storage status of the stored chemical products is judged to be abnormal. However, in large-scale chemical storage scenarios, the types of chemical products placed at the monitoring equipment locations are different, with varying properties, and each chemical product has different capabilities to affect the surrounding environment. The existing chemical storage and logistics management system's method of judging anomalies by setting fixed thresholds cannot reflect the unique risks of different chemical products, resulting in insufficient real-time monitoring and insufficient sensitivity in judging anomalies in the early stages. Summary of the Invention

[0004] This invention provides an Internet of Things-based safety monitoring, management and control system for chemical warehousing and logistics to solve existing problems.

[0005] The IoT-based chemical warehousing and logistics safety monitoring and management control system of the present invention adopts the following technical solution:

[0006] One embodiment of the present invention provides an Internet of Things-based chemical warehousing and logistics safety monitoring and management control system, which includes the following modules:

[0007] The acquisition module is used to acquire the monitoring value corresponding to each sensor in each integrated monitoring instrument;

[0008] The analysis module is used to determine the local significance of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times based on the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times; obtain the effective variation factor of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times based on the local significance of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times; and determine the environmental anomaly degree of each integrated monitoring instrument at the current time using the effective variation factor of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times.

[0009] The analysis module determines the local significance of the monitoring value of each sensor in each integrated monitoring instrument at different acquisition times based on the monitoring value of each sensor in each integrated monitoring instrument. The specific steps include the following:

[0010] Obtain the monitoring value at the nth collection time within the first time period;

[0011] The average value of the monitoring values ​​at the first n-1 collection times within the first time period is determined as the first average value;

[0012] The standard deviation of the monitoring values ​​at the first n-1 collection times within the first time period is determined as the first standard deviation;

[0013] Using the monitoring value, first mean, and first standard deviation at the nth acquisition time within the first time period, the local significance of the monitoring value corresponding to the ath sensor of the mth integrated monitoring instrument at the nth acquisition time is determined.

[0014] Obtain the local significance of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times;

[0015] The analysis module obtains the effective variation factor of the monitoring value of each sensor in each integrated monitoring instrument at different acquisition times based on the local significance of the monitoring value at different acquisition times. The specific steps include the following:

[0016] According to the time sequence, the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument is sorted from the second acquisition time to the d-th acquisition time to obtain the local significance sequence of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument; where the d-th acquisition time is the last acquisition time in the first time period;

[0017] Based on the positive and negative numbers in the local significance sequence of the monitoring values ​​corresponding to the a-th sensor of the m-th integrated monitoring instrument, the significance variation factor of the monitoring values ​​corresponding to the a-th sensor of the m-th integrated monitoring instrument is obtained.

[0018] Based on the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument, the effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the n-th acquisition time is obtained.

[0019] Obtain the effective variation factor of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times;

[0020] The analysis module utilizes the effective variation factor of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times to determine the environmental anomaly degree of each integrated monitoring instrument at the current time. The specific steps include the following:

[0021] The effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the second acquisition time and the effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the d-th acquisition time are determined as the second sum value.

[0022] The average of the effective variation factors of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument from the second acquisition time to the d-th acquisition time is determined as the second average.

[0023] Based on the second sum and the second mean, determine the environmental anomaly degree of the m-th integrated monitoring instrument at the current moment;

[0024] Obtain the environmental anomaly level of each integrated monitoring instrument at the current moment;

[0025] The control module is used to manage and control the chemical storage and logistics based on the environmental anomaly level of each integrated monitoring instrument at the current moment.

[0026] Furthermore, the acquisition module is specifically used for:

[0027] For the a-th sensor of the m-th integrated monitoring instrument, the moment when the sensor starts collecting data is taken as the start time, and the time period from the start time to the current time is taken as the first time period.

[0028] Acquire monitoring values ​​at all collection times within the first time period; where the collection time is determined based on the data collection frequency set by the sensor;

[0029] The monitoring values ​​collected at all times within the first time period are determined as the monitoring values ​​corresponding to the a-th sensor of the m-th integrated monitoring instrument.

[0030] Obtain the monitoring value corresponding to each sensor in each integrated monitoring instrument.

[0031] Furthermore, the specific steps for determining the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the n-th acquisition time using the monitoring value, the first mean, and the first standard deviation at the n-th acquisition time are as follows:

[0032] The difference between the monitored value at the nth collection time within the first time period and the first mean value is taken as the first difference value;

[0033] The cube of the ratio of the first difference to the first standard deviation is determined as the degree of deviation at the nth acquisition time within the first time period.

[0034] The deviations from the second to the nth acquisition time are summed, and the sum is determined as the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor at the n-th acquisition time.

[0035] Furthermore, the specific steps for obtaining the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument based on the positive and negative numbers in the local significance sequence of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument are as follows:

[0036] For the local significance sequence of the monitoring values ​​corresponding to the a-th sensor of the m-th integrated monitoring instrument, the ratio of the sum of all positive numbers to the sum of all negative numbers in the sequence is determined as the first ratio.

[0037] Subtract 1 from the absolute value of the first ratio to determine the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument.

[0038] Furthermore, the specific steps for obtaining the effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the nth acquisition time based on the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument are as follows:

[0039] The maximum value of the significance variation factor of the monitoring values ​​corresponding to all sensors of the m-th integrated monitoring instrument except for the a-th sensor is determined as the first maximum value;

[0040] The difference between the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the n-th acquisition time and the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the 2-th acquisition time is determined as the second difference.

[0041] The sum of the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument from the second acquisition time to the n-th acquisition time is determined as the first sum.

[0042] The absolute value of the ratio of the second difference to the first sum is determined as the first absolute value;

[0043] The ratio of the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument to the first maximum value is determined as the second ratio.

[0044] The product of the second ratio and the first absolute value is determined as the effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the n-th acquisition time.

[0045] Furthermore, the specific steps for determining the environmental anomaly degree of the m-th integrated monitoring instrument at the current moment based on the second sum and the second mean are as follows:

[0046] Subtract 2 from the ratio of the second sum to the second mean to determine the environmental anomaly degree of the a-th sensor of the m-th integrated monitoring instrument at the current moment;

[0047] Sum the environmental anomalies of all sensors of the m-th integrated monitoring instrument at the current time, and determine the sum as the environmental anomaly of the m-th integrated monitoring instrument at the current time.

[0048] Furthermore, the control module is specifically used for:

[0049] The environmental anomaly degree of each integrated monitoring instrument at the current time is normalized to obtain the normalized value of the environmental anomaly degree of each integrated monitoring instrument at the current time.

[0050] Based on the normalized value of the environmental anomaly degree of each integrated monitoring instrument at the current moment, obtain the visualization result of the environmental anomaly degree;

[0051] Based on the risk level of the environmental anomaly visualization results, chemical storage and logistics are managed and controlled.

[0052] The beneficial effects of the technical solution of this invention are as follows: This invention proposes an Internet of Things-based safety monitoring and management control system for chemical warehousing and logistics. By analyzing data collected by sensors in each integrated monitoring instrument, it obtains the environmental anomaly level of each integrated monitoring instrument at the current moment, and then manages and controls the chemical warehousing and logistics based on the environmental anomaly level of each integrated monitoring instrument at the current moment. This invention can improve the real-time performance of monitoring chemical warehousing and logistics and the sensitivity of judging the initial occurrence of anomalies. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a block diagram of the Internet of Things-based chemical warehousing and logistics safety monitoring, management and control system of the present invention. Detailed Implementation

[0055] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the Internet of Things-based chemical warehousing and logistics safety monitoring and management control system proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0057] The specific solution of the Internet of Things-based chemical warehousing and logistics safety monitoring, management and control system provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0058] Because hazardous chemicals are stored, chemical warehousing and logistics often rely on localized control through edge distributed nodes to more promptly and accurately identify abnormal stored chemicals. This invention models the edge distributed nodes based on environmental changes within their localized areas as identified by sensors. Furthermore, it analyzes the environmental change trends arising from the scale of abnormalities between these edge distributed nodes to determine safety events in chemical warehousing and promptly controls corresponding processes based on the evolving safety events.

[0059] This invention dynamically senses the local environment of edge distribution nodes and analyzes the abnormal environmental change trends formed by edge distribution nodes to achieve situation assessment based on the large-scale development of anomalies. This provides an intelligent judgment method for chemical storage and logistics safety monitoring systems, which significantly advances the warning window while reducing the false alarm rate. It also prevents judgment failures caused by the slow anomaly of some environments during the construction of chemical storage safety.

[0060] Please see Figure 1The diagram illustrates a block diagram of an IoT-based chemical warehousing and logistics safety monitoring and management control system according to an embodiment of the present invention. The system includes the following modules:

[0061] The acquisition module 100 is used to acquire the monitoring value corresponding to each sensor in each integrated monitoring instrument.

[0062] It should be noted that the integrated monitoring system integrates multiple monitoring devices on a single host unit and connects to a central server via wireless / wired connections, thereby achieving accurate detection of various local areas within a large-scale warehouse environment. The monitoring devices integrated into the host unit include: temperature and humidity sensors: detecting the temperature and humidity of the surrounding air; smoke sensors: detecting the smoke concentration in the surrounding environment to determine the potential fire risk; and various gas sensors: such as carbon monoxide (CO), carbon dioxide (CO2), and hydrogen sulfide (H2S), to sense the distribution of harmful gases in the surrounding environment.

[0063] The integrated monitoring instrument records real-time monitoring data locally through the core microprocessor (MCU) and data storage unit integrated inside the host. At the same time, the recorded data is transmitted to the central server in real time through the wireless communication module (wireless local area network in the warehouse). The central server stores the device ID and the returned data from the device, thereby completing the environmental monitoring and identification of various locations in the chemical storage and logistics.

[0064] Different sensors correspond to different monitoring values.

[0065] Obtaining module 100 specifically includes steps S011-S014:

[0066] Step S011: For the a-th sensor of the m-th integrated monitor, take the moment when the sensor starts collecting data as the start time, and take the time period from the start time to the current time as the first time period.

[0067] It should be noted that large-scale chemical warehouses are equipped with multiple integrated monitoring instruments, each containing multiple sensors. The time elapsed from the initial time t0 to the current time t is defined as the first time period.

[0068] Step S012: Obtain the monitoring values ​​at all collection times within the first time period; wherein, the collection time is determined according to the data collection frequency set by the sensor.

[0069] It should be noted that the sampling frequency is set according to the specific scenario; in this embodiment, it is 1 sampling per second.

[0070] Step S013: Determine the monitoring values ​​of all acquisition times within the first time period as the monitoring values ​​corresponding to the a-th sensor of the m-th integrated monitoring instrument.

[0071] Step S014: Obtain the monitoring value corresponding to each sensor in each integrated monitoring instrument.

[0072] The analysis module 200 is used to determine the local significance of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times based on the monitoring value corresponding to each sensor in each integrated monitoring instrument; to obtain the effective variation factor of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times based on the local significance of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times; and to determine the environmental anomaly degree of each integrated monitoring instrument at the current time using the effective variation factor of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times.

[0073] It is important to note that the analysis first focuses on localized anomalies in large-scale warehousing environments. In large-scale chemical storage, due to the diversity and specificity of stored chemicals, the core risk lies in localized microenvironmental anomalies. Specific chemicals may, through slow evaporation, minor leaks, or self-reactions, create changes in a particular container, pallet, or corner that differ from the surrounding environment (e.g., thermal decomposition leading to a localized increase in gas concentration, exceeding normal atmospheric concentrations, resulting in deposition within a localized area). These anomalies are highly concealed and localized; their impact is initially extremely limited and difficult for macroscopic environmental monitoring systems to detect. Therefore, it is necessary to model the local characteristics of the integrated monitoring instrument's monitoring attributes within its localized area to accurately assess microenvironmental changes at the instrument's location.

[0074] For the m-th integrated monitoring instrument, the monitoring attribute corresponding to the a-th sensor installed on it is first extracted by extracting the fluctuation of a single attribute to highlight the abnormal attributes in the current local area. Then, the micro-environment parameters in the local area of ​​the m-th integrated monitoring instrument are evaluated by comprehensively considering the abnormal distribution of multiple attributes in the local area of ​​the m-th integrated monitoring instrument.

[0075] The analysis module determines the local significance of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times based on the monitoring value of each sensor in each integrated monitoring instrument, including steps S021-S025:

[0076] Step S021: Obtain the monitoring value at the nth collection time within the first time period.

[0077] It should be noted that the monitoring value at the nth acquisition time within the first time period is denoted as... .

[0078] Step S022: Determine the average value of the monitoring values ​​at the first n-1 collection times within the first time period as the first average value.

[0079] It should be noted that the first mean is denoted as... .

[0080] Step S023: Determine the standard deviation of the monitoring values ​​at the first n-1 collection times within the first time period as the first standard deviation.

[0081] It should be noted that the first standard deviation is denoted as... .

[0082] For example, there are 5 sampling times in the first time period, and the monitoring value at the 3rd sampling time is obtained. Then calculate the mean of the monitored values ​​at the first and second sampling times. and standard deviation .

[0083] Step S024: Using the monitoring value, the first mean, and the first standard deviation at the nth acquisition time within the first time period, determine the local significance of the monitoring value corresponding to the ath sensor of the mth integrated monitoring instrument at the nth acquisition time.

[0084] Step S024 further includes steps S0241-S0243:

[0085] Step S0241: Take the difference between the monitored value at the nth collection time within the first time period and the first mean as the first difference.

[0086] It should be noted that the first difference is denoted as: .

[0087] Step S0242: Calculate the cube of the ratio of the first difference to the first standard deviation as the degree of deviation at the nth acquisition time within the first time period.

[0088] It should be noted that the deviation at the nth acquisition time within the first time period is denoted as: .

[0089] Step S0243: Sum the deviations from the second acquisition time to the nth acquisition time, and determine the sum as the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor at the nth acquisition time.

[0090] Specifically:

[0091]

[0092] in, This represents the local significance of the monitored value corresponding to the a-th sensor of the m-th integrated monitor at the n-th acquisition time. N represents the number of sampling times from the 2nd sampling time to the n-th acquisition time. This reflects the degree and direction of deviation between the monitored value at the nth acquisition time within the first time period and the monitored values ​​in the earlier parts of the time series. The difference is amplified by cube calculation, and the numerical signs between the monitored values ​​are preserved to determine the direction of fluctuation, thus effectively extracting the single-attribute fluctuation process. Furthermore, real-time judgment of monitored attribute a (the monitored value corresponding to the a-th sensor of the m-th integrated monitoring instrument) is performed by traversing from the 2nd sampling time to the nth acquisition time.

[0093] Step S025: Obtain the local significance of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times.

[0094] The analysis module obtains the effective variation factor of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times based on the local significance of the monitoring value at different acquisition times, including steps S031-S034:

[0095] It should be noted that: further evaluation of local sensitivity is conducted by combining the local output characteristics of the m-th integrated monitoring instrument with the local significance distribution of the monitored local data attributes. In the local area monitored by the m-th integrated monitoring instrument, abnormal changes often occur first in individual attributes, which then lead to changes in regional attributes. Therefore, the output judgment of the m-th integrated monitoring instrument is made by combining the significance fluctuation analysis between attributes in the local area.

[0096] Step S031: Sort the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor at the second acquisition time to the d-th acquisition time according to the time sequence, and obtain the local significance sequence of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor; wherein the d-th acquisition time is the last acquisition time in the first time period.

[0097] For example, the first time period has 5 sampling times, and each sampling time (except for the first sampling time) corresponds to a local significance. Then, the local significance sequence of the monitored values ​​corresponding to the a-th sensor of the m-th integrated monitoring instrument is [ , ].

[0098] It should be noted that the frequency of all attribute collections and the frequency of data uploads to the server are consistent, so the sequence lengths are the same.

[0099] Step S032: Based on the positive and negative numbers in the local significance sequence of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor, obtain the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor.

[0100] Step S032 further includes steps S0321-S0322:

[0101] Step S0321: For the local significance sequence of the monitoring values ​​corresponding to the a-th sensor of the m-th integrated monitoring instrument, the ratio of the sum of all positive numbers to the sum of all negative numbers in the sequence is determined as the first ratio.

[0102] It should be noted that: The local saliency sequence is divided into positive and negative parts centered at 0, yielding all positive and all negative numbers in the sequence. The sum of all positive numbers in the sequence is denoted as... The sum of all negative numbers in the sequence is denoted as . .

[0103] The first ratio, denoted as .

[0104] Step S0322: Subtract 1 from the absolute value of the first ratio to determine the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument.

[0105] Specifically:

[0106]

[0107] in, This represents the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument.

[0108] Step S033: Based on the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor, obtain the effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor at the n-th acquisition time.

[0109] Step S033 further includes steps S0331-S0336:

[0110] Step S0331: Determine the maximum value of the significance variation factor of the monitoring values ​​corresponding to all sensors of the m-th integrated monitoring instrument except for the a-th sensor as the first maximum value.

[0111] It should be noted that the first maximum value is denoted as: .

[0112] Step S0332: The difference between the local significance of the monitoring value corresponding to the a sensor of the m-th integrated monitor at the n-th acquisition time and the local significance of the monitoring value corresponding to the a sensor of the m-th integrated monitor at the 2-th acquisition time is determined as the second difference.

[0113] It should be noted that the second difference is denoted as... .

[0114] Step S0333: The sum of the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor at the second acquisition time to the n-th acquisition time is determined as the first sum.

[0115] It should be noted that the first sum is denoted as: .

[0116] Step S0334: Determine the absolute value of the ratio of the second difference to the first sum as the first absolute value.

[0117] It should be noted that the first absolute value is denoted as: .

[0118] Step S0335: The ratio of the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor to the first maximum value is determined as the second ratio.

[0119] It should be noted that the second ratio is denoted as: .

[0120] Step S0336: The product of the second ratio and the first absolute value is determined as the effective variation factor of the monitoring value corresponding to the a sensor of the m-th integrated monitoring instrument at the n-th acquisition time.

[0121] Specifically,

[0122]

[0123] in, This represents the effective variation factor of the monitored value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the n-th acquisition time. This reflects the prominence of the significance variation factor of the monitoring value corresponding to the a sensor of the m-th integrated monitoring instrument among all attributes. The larger this formula is, the more obvious the environmental impact factor represented by the current attribute is on the location of the m-th integrated monitoring instrument (such as the decomposition of nitro compounds during storage due to their unstable properties, which generates heat, and the heat release also aggravates the decomposition of surrounding substances, thus creating a cycle).

[0124] Simultaneously, after assessing the impact of current environmental factors through the proportion of significance, it is necessary to judge the level of fluctuation of significance over time. This is to avoid a slow response process that leads to slow outlier changes in significance, thus missing abnormal environmental changes. Therefore, combining... The variation in the significance at the current moment and the fluctuation level of the overall significance are shown, thus enabling accurate identification of slow anomalies in the local environment.

[0125] Step S034: Obtain the effective variation factor of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times.

[0126] The analysis module utilizes the effective variation factor of the monitored values ​​corresponding to each sensor in each integrated monitoring instrument at different acquisition times to determine the environmental anomaly degree of each integrated monitoring instrument at the current time, including steps S041-S044:

[0127] It should be noted that the analysis of the local significance distribution within the range of the m-th integrated monitoring instrument shows that local significance represents the actual local trend of the environmental monitoring data represented by monitoring attribute a, i.e., the data changes caused by the unique properties of chemicals stored near the m-th integrated monitoring instrument. This indicates that the more attributes with high significance fluctuations, the more obvious the distinction between significant fluctuations of different attributes, indicating that the unique properties of the current chemicals are less likely to be similar to other factors causing environmental changes, thus improving the accuracy of the m-th integrated monitoring instrument in detecting anomalies in the surrounding neighboring areas.

[0128] Step S041: The effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor at the second acquisition time and the effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor at the d-th acquisition time are determined as the second sum value.

[0129] It should be noted that the second sum is denoted as... ,in This represents the effective variation factor of the monitored value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the d-th acquisition time. This represents the effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the second acquisition time.

[0130] Step S042: The average of the effective variation factors of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument from the second acquisition time to the d-th acquisition time is determined as the second average.

[0131] It should be noted that the second mean is denoted as... .

[0132] Step S043: Determine the environmental anomaly degree of the m-th integrated monitoring instrument at the current moment based on the second sum and the second mean.

[0133] Step S043 further includes steps S0431-S0432:

[0134] Step S0431: Subtract 2 from the ratio of the second sum to the second mean to determine the environmental anomaly degree of the a-th sensor of the m-th integrated monitoring instrument at the current moment.

[0135] It should be noted that the environmental anomaly degree of the m-th integrated monitoring instrument and the a-th sensor at the current moment is denoted as: .

[0136] Step S0432: Sum the environmental anomaly degrees of all sensors of the m-th integrated monitoring instrument at the current time, and determine the sum as the environmental anomaly degree of the m-th integrated monitoring instrument at the current time.

[0137] Specifically,

[0138]

[0139] in, This represents the degree of environmental anomaly of the m-th integrated monitoring instrument at the current time t. This represents the number of sensors contained in the m-th integrated monitoring device. This formula obtains the anomaly status of a single environmental influencing factor around the m-th integrated monitoring instrument at the current time t by combining the current state and the initial state, and assesses the effectiveness of its impact on the surrounding environment. By using -2 to adjust the value range to fluctuate around 0, the direction of anomaly fluctuation can be more clearly determined through single attributes. Finally, by traversing the integrated monitoring attributes in the m-th integrated monitoring instrument, the sum of the current environmental influence at the current time is obtained, thus completing the judgment of the abnormal monitoring value of a single integrated monitoring instrument.

[0140] Step S044: Obtain the environmental anomaly level of each integrated monitoring instrument at the current moment.

[0141] The control module 300 is used to manage and control the chemical storage and logistics based on the environmental anomaly level of each integrated monitoring instrument at the current moment.

[0142] Control module 300 specifically includes steps S051-S053:

[0143] Step S051: Normalize the environmental anomaly degree of each integrated monitoring instrument at the current time to obtain the normalized value of the environmental anomaly degree of each integrated monitoring instrument at the current time.

[0144] Step S052: Obtain the environmental anomaly visualization result based on the normalized value of the environmental anomaly degree of each integrated monitoring instrument at the current time.

[0145] Step S053: Based on the risk level of the environmental anomaly visualization results, manage and control the chemical storage and logistics.

[0146] Specifically, after receiving environmental anomaly reports from each distributed integrated monitoring instrument, the central server dynamically and multi-dimensionally visualizes them on the electronic map of the management platform:

[0147] Dynamic heatmap overlay: The environmental anomalies received from each location are overlaid on the warehouse floor plan or 3D model in the form of a heatmap. The environmental anomalies are normalized by a normalization function, and the color depth of the false color display (such as from blue to red) is assigned according to the normalization value to intuitively represent the strength of the anomalies, so that managers can easily locate the location of high anomaly areas.

[0148] Multi-layer information integration: Based on the heat map, accurately mark the location of all relevant integrated monitoring instruments (the installation location of the integrated monitoring instruments is prior) and the real-time value of attributes that have reached the abnormal threshold (e.g., temperature threshold of 25 degrees, actual temperature of 47 degrees).

[0149] Linking abnormal areas with the warehouse information database: The abnormal integrated monitoring instrument will automatically display a list of chemicals stored in the coordinate area, MSDS (Safety Data Sheet), and emergency response plan.

[0150] Early warning escalation and linkage: Based on the risk level presented by the visualization results, the system automatically triggers different levels of early warnings, such as linking the activation of forced ventilation in the area, closing fire doors, or dispatching robots / personnel to handle the situation, thereby realizing the safety monitoring, management and control of chemical storage and logistics.

[0151] In summary, in this embodiment of the invention, by analyzing the data collected by the sensors in each integrated monitoring instrument, the environmental anomaly level of each integrated monitoring instrument at the current moment is obtained, and then the chemical storage and logistics are managed and controlled based on the environmental anomaly level of each integrated monitoring instrument at the current moment.

[0152] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A chemical warehousing and logistics safety monitoring, management, and control system based on the Internet of Things, characterized in that, The system includes the following modules: The acquisition module is used to acquire the monitoring value corresponding to each sensor in each integrated monitoring instrument; The analysis module is used to determine the local significance of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times, based on the monitoring value corresponding to each sensor in each integrated monitoring instrument. Based on the local significance of the monitoring values ​​corresponding to each sensor in each integrated monitoring instrument at different acquisition times, the effective variation factor of the monitoring values ​​corresponding to each sensor in each integrated monitoring instrument at different acquisition times is obtained; using the effective variation factor of the monitoring values ​​corresponding to each sensor in each integrated monitoring instrument at different acquisition times, the environmental anomaly degree of each integrated monitoring instrument at the current time is determined. The analysis module determines the local significance of the monitoring value of each sensor in each integrated monitoring instrument at different acquisition times based on the monitoring value of each sensor in each integrated monitoring instrument. The specific steps include the following: Obtain the monitoring value at the nth collection time within the first time period; The average value of the monitoring values ​​at the first n-1 collection times within the first time period is determined as the first average value; The standard deviation of the monitoring values ​​at the first n-1 collection times within the first time period is determined as the first standard deviation; Using the monitoring value, first mean, and first standard deviation at the nth acquisition time within the first time period, the local significance of the monitoring value corresponding to the ath sensor of the mth integrated monitoring instrument at the nth acquisition time is determined. Obtain the local significance of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times; The analysis module obtains the effective variation factor of the monitoring value of each sensor in each integrated monitoring instrument at different acquisition times based on the local significance of the monitoring value at different acquisition times. The specific steps include the following: According to the time sequence, the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument is sorted from the second acquisition time to the d-th acquisition time to obtain the local significance sequence of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument; where the d-th acquisition time is the last acquisition time in the first time period; Based on the positive and negative numbers in the local significance sequence of the monitoring values ​​corresponding to the a-th sensor of the m-th integrated monitoring instrument, the significance variation factor of the monitoring values ​​corresponding to the a-th sensor of the m-th integrated monitoring instrument is obtained. Based on the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument, the effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the n-th acquisition time is obtained. The effective variation factor of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times is obtained. Specifically, the analysis module uses the effective variation factor of the monitoring value corresponding to each sensor in each integrated monitoring instrument at different acquisition times to determine the environmental anomaly degree of each integrated monitoring instrument at the current time. The specific steps include the following: The effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the second acquisition time and the effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the d-th acquisition time are determined as the second sum value. The average of the effective variation factors of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument from the second acquisition time to the d-th acquisition time is determined as the second average. Based on the second sum and the second mean, determine the environmental anomaly degree of the m-th integrated monitoring instrument at the current moment; Obtain the environmental anomaly level of each integrated monitoring instrument at the current moment; The control module is used to manage and control the chemical storage and logistics based on the environmental anomaly level of each integrated monitoring instrument at the current moment.

2. The IoT-based chemical warehousing and logistics safety monitoring and management control system according to claim 1, characterized in that, The acquisition module is specifically used for: For the a-th sensor of the m-th integrated monitoring instrument, the moment when the sensor starts collecting data is taken as the start time, and the time period from the start time to the current time is taken as the first time period. Acquire monitoring values ​​at all collection times within the first time period; where the collection time is determined based on the data collection frequency set by the sensor; The monitoring values ​​collected at all times within the first time period are determined as the monitoring values ​​corresponding to the a-th sensor of the m-th integrated monitoring instrument. Obtain the monitoring value corresponding to each sensor in each integrated monitoring instrument.

3. The IoT-based chemical warehousing and logistics safety monitoring and management control system according to claim 1, characterized in that, The specific steps for determining the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the n-th acquisition time using the monitoring value, the first mean, and the first standard deviation at the n-th acquisition time are as follows: The difference between the monitored value at the nth collection time within the first time period and the first mean value is taken as the first difference value; The cube of the ratio of the first difference to the first standard deviation is determined as the degree of deviation at the nth acquisition time within the first time period. The deviations from the second to the nth acquisition time are summed, and the sum is determined as the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitor at the n-th acquisition time.

4. The IoT-based chemical warehousing and logistics safety monitoring and management control system according to claim 1, characterized in that, The specific steps for obtaining the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument based on the positive and negative numbers in the local significance sequence of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument are as follows: For the local significance sequence of the monitoring values ​​corresponding to the a-th sensor of the m-th integrated monitoring instrument, the ratio of the sum of all positive numbers to the sum of all negative numbers in the sequence is determined as the first ratio. Subtract 1 from the absolute value of the first ratio to determine the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument.

5. The IoT-based chemical warehousing and logistics safety monitoring and management control system according to claim 1, characterized in that, The specific steps for obtaining the effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the nth acquisition time, based on the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument, are as follows: The maximum value of the significance variation factor of the monitoring values ​​corresponding to all sensors of the m-th integrated monitoring instrument except for the a-th sensor is determined as the first maximum value; The difference between the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the n-th acquisition time and the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the 2-th acquisition time is determined as the second difference. The sum of the local significance of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument from the second acquisition time to the n-th acquisition time is determined as the first sum. The absolute value of the ratio of the second difference to the first sum is determined as the first absolute value; The ratio of the significance variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument to the first maximum value is determined as the second ratio. The product of the second ratio and the first absolute value is determined as the effective variation factor of the monitoring value corresponding to the a-th sensor of the m-th integrated monitoring instrument at the n-th acquisition time.

6. The IoT-based chemical warehousing and logistics safety monitoring and management control system according to claim 1, characterized in that, The specific steps for determining the environmental anomaly degree of the m-th integrated monitoring instrument at the current moment based on the second sum and the second mean are as follows: Subtract 2 from the ratio of the second sum to the second mean to determine the environmental anomaly degree of the a-th sensor of the m-th integrated monitoring instrument at the current moment; Sum the environmental anomalies of all sensors of the m-th integrated monitoring instrument at the current time, and determine the sum as the environmental anomaly of the m-th integrated monitoring instrument at the current time.

7. The IoT-based chemical warehousing and logistics safety monitoring and management control system according to claim 1, characterized in that, The control module is specifically used for: The environmental anomaly degree of each integrated monitoring instrument at the current time is normalized to obtain the normalized value of the environmental anomaly degree of each integrated monitoring instrument at the current time. Based on the normalized value of the environmental anomaly degree of each integrated monitoring instrument at the current moment, obtain the visualization result of the environmental anomaly degree; Based on the risk level of the environmental anomaly visualization results, chemical storage and logistics are managed and controlled.

Images