Storage environment intelligent monitoring and early warning method and system based on Internet of Things

Abstract

The invention relates to a storage environment intelligent monitoring and early warning method and system based on the Internet of Things, and belongs to the field of storage safety monitoring. The method comprises the following steps: acquiring an original data packet of a storage environment, and detecting and extracting a disturbance signal; constructing a physical field back propagation model based on the disturbance signal, and separating an abnormal source; constructing a risk assessment model based on the abnormal source, and generating a dynamic risk thermodynamic diagram; and performing plan simulation based on the dynamic risk thermodynamic diagram and outputting an optimal plan instruction set. According to the method, the physical field back propagation model, the dynamic risk thermodynamic diagram and the plan simulation optimization mechanism are constructed, so that the defects of the prior art in the aspects of traceability, risk assessment dynamics and decision-making intelligence are overcome, and a systematic solution is provided for realizing intelligent storage safety management and control in a real sense.

Description

Technical Field

[0001] This invention belongs to the field of warehouse safety monitoring technology, specifically relating to an intelligent monitoring and early warning method and system for warehouse environment based on the Internet of Things. Background Technology

[0002] With the rapid development of the Internet of Things (IoT), sensor technology, and artificial intelligence (AI), modern warehouse environment monitoring systems have evolved from traditional single-sensor alarms to multi-sensor fusion and intelligent analysis. Existing technologies mainly include independent sensor alarm systems based on fixed threshold triggers, simple status monitoring platforms based on data fusion, and rudimentary intelligent systems utilizing machine learning for anomaly detection. However, these methods still have significant shortcomings: First, most systems can only provide anomaly alarms and cannot accurately locate and trace the source of the anomaly, especially in complex warehouse environments where the coupling of multiple physical fields makes it difficult for a single sensor to distinguish the cause of the anomaly. Second, existing risk assessments largely rely on human experience or static rules, lacking dynamic comprehensive assessment of multi-dimensional information such as cargo value, environmental vulnerability, and time factors, leading to delayed or overreacting risk responses. Third, contingency plan execution often relies on fixed procedures, lacking rapid simulation and optimization mechanisms in digital twin environments, making it difficult to make scientific decisions in emergency situations. Therefore, there is an urgent need for an intelligent warehouse environment monitoring system capable of achieving a closed-loop end-to-end system to improve the foresight, accuracy, and automation level of warehouse safety management. Summary of the Invention

[0003] To address the aforementioned problems in the existing technology, this invention provides a method and system for intelligent monitoring and early warning of warehouse environment based on the Internet of Things.

[0004] The objective of this invention can be achieved through the following technical solutions: A method for intelligent monitoring and early warning of warehouse environment based on the Internet of Things (IoT), the implementation of which includes the following steps: Step S1: Collect raw data packets of the storage environment and detect and extract disturbance signals; Step S2: Construct a physical field backpropagation model based on the disturbance signal to isolate the anomaly source; Step S3: Construct a risk assessment model based on the anomaly source and generate a dynamic risk heat map; Step S4: Based on the dynamic risk heat map, perform contingency plan simulation and output the optimal contingency plan instruction set.

[0005] Preferably, the detection and extraction of the disturbance signal in step S1 specifically includes: The raw data packet contains the sensor ID, timestamp, and measurement value; Align the data to a uniform time grid and remove erroneous data; Learn the behavior patterns of each sensor under historical normal conditions; The system monitors in real time whether the data in the original data packet deviates from the behavior pattern under historical normal conditions. For data marked as abnormal changes, a time series signal is extracted as the perturbation signal. Each perturbation signal includes the signal source, signal type, signal strength, and time range.

[0006] Preferably, the construction of the physical field backpropagation model in step S2 specifically involves: Establish a physical model of the warehouse, and input the physical structure of the warehouse, the thermal properties of the building materials, and the airflow pattern of the ventilation system into the system; The anomaly source is obtained by reverse tracing using the reverse source equation, and its mathematical description is as follows: ,in, Let be a normalized source term vector, representing the release intensity of the j-th type of source per unit volume and per unit time. It has a dimension of m×1, where m is the number of possible source types. This is a normalized observation vector with dimensions n×1, where n is the number of monitored physical quantities. The normalized Green's tensor has dimensions n×m, and the elements in the matrix are... Characterized at position x, time Release unit intensity of type j source, for location The influence of the i-th type of observation at time t For regularization terms, The regularization coefficient is . For tracing the time window, The spatial integration region is represented; each of the anomaly sources includes the source location, source type, source strength, and confidence level.

[0007] Preferably, the construction of the risk assessment model in step S3 specifically involves: S301: Construct a dynamic risk quantification index based on the aforementioned anomaly source, mathematically described as follows: ,in, As a dynamic risk quantification indicator, Weighting based on the value of goods. Let be the vulnerability function of the goods. Due to deviations in environmental parameters, The safety deviation threshold for environmental parameters, Time weighting; The dynamic risk heatmap is generated based on the dynamic risk quantification index.

[0008] Preferably, the simulation of the contingency plan in step S4 specifically includes: Early warning information is generated based on the dynamic risk quantification indicators described in the dynamic risk heatmap; Multiple contingency plans are preset, and the net effect of each plan is simulated in the digital twin. Mathematically, this can be described as... ,in, For the net effect of plan P, To determine the risk value at position x before implementing the contingency plan P, To determine the risk value at position x after implementing contingency plan P, This is the penalty coefficient for side effects. The side effects of plan P at position k; The optimal contingency plan instruction set is output based on the net effect.

[0009] An IoT-based intelligent monitoring and early warning system for warehouse environment is used to execute the IoT-based intelligent monitoring and early warning method for warehouse environment described above, including a disturbance extraction module, a reverse tracing module, a risk assessment module, and a contingency plan simulation module. The disturbance extraction module is used to collect raw data packets of the storage environment and detect and extract disturbance signals; The reverse tracing module is used to construct a physical field back propagation model based on the disturbance signal and separate the source of the anomaly. The risk assessment module is used to construct a risk assessment model based on the anomaly source and generate a dynamic risk heat map. The contingency plan simulation module is used to simulate contingency plans based on the dynamic risk heat map and output the optimal contingency plan instruction set.

[0010] The beneficial effects of this invention are as follows: (1) By using multi-sensor data fusion and physical field backpropagation model, not only can anomalies be detected, but also the source of anomalies (such as equipment failure, heat intrusion, initial fire, etc.) can be quickly located, improving response efficiency and enhancing the accuracy and real-time performance of anomaly detection and tracing.

[0011] (2) By constructing a dynamic risk heat map, the abstract risk is transformed into an intuitive spatial distribution map. Combined with factors such as cargo value and time weight, risk visualization and dynamic assessment are achieved, which facilitates risk quantitative management.

[0012] (3) Simulate the effects of multiple contingency plans in a digital twin environment, comprehensively consider risk reduction and side effects, output the optimal instruction set, improve the intelligence level of emergency decision-making, and enhance the scientific nature and adaptability of contingency plan decision-making.

[0013] (4) By learning from historical behavior patterns and conducting joint analysis of multiple signals, false alarms caused by environmental fluctuations can be reduced, while improving the ability to identify potential risks in the early stages. Attached Figure Description

[0014] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0015] Figure 1 This is a flowchart illustrating the steps of an IoT-based intelligent monitoring and early warning method for warehouse environments according to the present invention. Detailed Implementation

[0016] To better understand the invention, various aspects of the invention will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are merely illustrative of exemplary embodiments of the invention and are not intended to limit the scope of the invention in any way. Throughout the specification, the expression "and / or" includes any and all combinations of one or more of the associated listed items. As used herein, the terms "approximately," "about," and similar terms are used as expressions of approximation, not as expressions of degree, and are intended to describe inherent deviations in measured or calculated values ​​that will be recognized by those skilled in the art. Furthermore, the order in which the steps are described in this invention does not necessarily indicate the order in which these steps occur in actual operation, unless otherwise expressly defined or deduced from the context.

[0017] It should also be understood that expressions such as "comprising," "including," "having," "containing," and / or "comprising" are open-ended rather than closed-ended expressions in this specification, indicating the presence of the stated features, elements, and / or components, but not excluding the presence of one or more other features, elements, components, and / or combinations thereof. Furthermore, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features, not just individual elements in the list. Additionally, when describing embodiments of the invention, the word "may" is used to mean "one or more embodiments of the invention." And the term "exemplary" is intended to refer to examples or illustrations.

[0018] Unless otherwise specified, all terms used herein (including engineering and technical terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that, unless expressly stated herein, terms defined in common dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the relevant art, and not in an idealized or overly formalized sense.

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other. The invention will now be described in detail with reference to the accompanying drawings and embodiments. Example 1: Please see Figure 1A method for intelligent monitoring and early warning of warehouse environment based on the Internet of Things, comprising: Step S1: Collect raw data packets of the storage environment and detect and extract disturbance signals; Step S2: Construct a physical field backpropagation model based on the disturbance signal to isolate the anomaly source; Step S3: Construct a risk assessment model based on the anomaly source and generate a dynamic risk heat map; Step S4: Based on the dynamic risk heat map, perform contingency plan simulation and output the optimal contingency plan instruction set.

[0020] In this embodiment, the detection and extraction of the disturbance signal specifically involves: S101: Various sensors (temperature, humidity, smoke, VOC, etc.) are deployed in the warehouse. Each sensor sends a raw data packet to the central server every few seconds. The raw data packet contains the sensor ID, timestamp, and measurement value. For example, temperature sensor T-001 measured 25.3℃ at 14:00:00 on 2025-1-1. S102: The server aligns data from different sensors and timestamps to a unified time grid and removes obviously erroneous data (such as instantaneous jumps to extreme values). S103: Learn the behavior patterns of each sensor under historical normal conditions, including typical values, range of change, and rate of change at different times of the day. For example, the temperature sensor on the east side of the warehouse is usually between 24-26°C at 2 pm and changes slowly. S104: Monitor in real time whether the data in the original data packet deviates from the behavior pattern under the historical normal conditions. For data marked as abnormal changes, extract a time series signal containing the time from the beginning of the change to the current moment as the disturbance signal. Each disturbance signal contains the signal source (which sensor it comes from), signal type (temperature, humidity or other), signal strength (the degree of deviation from the normal pattern at present) and time range. For example, signal 1: Sensor T-001 (located in the southeast corner of the warehouse) temperature abnormally increased by 0.3℃ (in the past 10 minutes).

[0021] In this embodiment, the construction of the physical field backpropagation model is specifically as follows: S201: Establish a physical model of the warehouse, which involves inputting the physical structure of the warehouse (walls, shelves, ventilation duct layout), the thermal properties of building materials (such as thermal conductivity), and the airflow pattern of the ventilation system into the system (or obtaining it through inversion from sensor data); the physical model of the warehouse describes how heat, humidity, smoke, etc., spread within the warehouse; S202: Reverse source tracing is performed using a reverse source tracing equation (simultaneously processing the tracing of multiple abnormal signals such as temperature, humidity, smoke concentration, and VOC concentration), and the source of the anomaly is obtained by solving the equation. The mathematical description is as follows: ,in, Let be a normalized source term vector, representing the release intensity of the j-th type of source per unit volume and per unit time. It has a dimension of m×1, where m is the number of possible source types. This is a normalized observation vector (derived from the disturbance signal), with dimensions n×1, where n is the number of monitored physical quantities. The normalized Green's tensor has dimensions n×m, and the elements in the matrix are... Characterized at position x, time Release unit intensity of type j source, for location The dimensionless influence of the i-th type of observation at time t For regularization terms, The regularization coefficient is . For tracing the time window, The spatial integration region is represented; each of the aforementioned anomaly sources includes the source location (three-dimensional coordinates within the warehouse), source type (which may be equipment failure, external heat intrusion, initial stage of fire, etc.), source intensity (heating rate, release rate, etc.), and confidence level (confidence score calculated based on the model fit).

[0022] In this embodiment, the risk assessment model is constructed as follows: S301: Construct a dynamic risk quantification index based on the aforementioned anomaly source, mathematically described as follows: ,in, It is a dynamic risk quantification indicator (the higher the value, the higher the risk). Weighting is based on the value of the goods (valuable goods have higher weighting). Let be the cargo vulnerability function, to reflect the non-linear increase in vulnerability with the degree of deviation. This is due to deviations in environmental parameters (originating from disturbance signals). The safety deviation threshold for environmental parameters, Time-weighted, for example, the risk cost is higher when there is no one on duty at night; S302: Generate the dynamic risk heat map based on the dynamic risk quantification index.

[0023] In this embodiment, the simulation of the contingency plan specifically refers to: S401: Generate early warning information based on the level and diffusion speed of the dynamic risk quantification indicators in the dynamic risk heat map; for example, Level 1 early warning information: low risk value, reminding the administrator to pay attention to changes in a certain area; Level 2 early warning information: medium risk value, requiring manual or automatic intervention; Level 3 early warning information: high risk value, requiring immediate automatic handling and notification to multiple parties; S402: Pre-set multiple contingency plans and quickly simulate the net effect of each plan in a digital twin (a virtual model of the warehouse). Mathematically described as follows: ,in, For the net effect of plan P, To determine the risk value at position x before implementing the contingency plan P, To determine the risk value at position x after implementing contingency plan P, This is the penalty coefficient for side effects. The side effects of contingency plan P at position k are defined as the new risk value caused by the execution of the contingency plan. S403: Output the optimal contingency plan instruction set based on the net effect.

[0024] Example 2: An intelligent monitoring and early warning system for warehouse environment based on the Internet of Things includes a disturbance extraction module, a reverse tracing module, a risk assessment module, and a contingency plan simulation module; The disturbance extraction module is used to collect raw data packets of the storage environment and detect and extract disturbance signals; The reverse tracing module is used to construct a physical field back propagation model based on the disturbance signal and separate the source of the anomaly. The risk assessment module is used to construct a risk assessment model based on the anomaly source and generate a dynamic risk heat map. The contingency plan simulation module is used to simulate contingency plans based on the dynamic risk heat map and output the optimal contingency plan instruction set.

[0025] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for intelligent monitoring and early warning of warehouse environment based on the Internet of Things, characterized in that, Includes the following steps: Step S1: Collect raw data packets of the storage environment and detect and extract disturbance signals; Step S2: Construct a physical field backpropagation model based on the disturbance signal to isolate the anomaly source; Step S3: Construct a risk assessment model based on the anomaly source and generate a dynamic risk heat map; Step S4: Based on the dynamic risk heat map, perform contingency plan simulation and output the optimal contingency plan instruction set.

2. The method for intelligent monitoring and early warning of warehouse environment based on the Internet of Things according to claim 1, characterized in that, The detection and extraction of the disturbance signal in step S1 specifically involves: The raw data packet contains the sensor ID, timestamp, and measurement value; Align the data to a uniform time grid and remove erroneous data; Learn the behavior patterns of each sensor under historical normal conditions; The system monitors in real time whether the data in the original data packet deviates from the behavior pattern under historical normal conditions. For data marked as abnormal changes, a time series signal is extracted as the perturbation signal. Each perturbation signal includes the signal source, signal type, signal strength, and time range.

3. The intelligent monitoring and early warning method for warehouse environment based on the Internet of Things according to claim 1, characterized in that, The construction of the physical field backpropagation model in step S2 is specifically as follows: Establish a physical model of the warehouse, and input the physical structure of the warehouse, the thermal properties of the building materials, and the airflow pattern of the ventilation system into the system; The anomaly source is obtained by reverse tracing using the reverse source equation, and its mathematical description is as follows: ,in, Let be a normalized source term vector, representing the release intensity of the j-th type of source per unit volume and per unit time. It has a dimension of m×1, where m is the number of possible source types. This is a normalized observation vector with dimensions n×1, where n is the number of monitored physical quantities. The normalized Green's tensor has dimensions n×m, and the elements in the matrix are... Characterized at position x, time Release unit intensity of type j source, for location The influence of the i-th type of observation at time t For regularization terms, The regularization coefficient is . For tracing the time window, The spatial integration region is represented; each of the anomaly sources includes the source location, source type, source strength, and confidence level.

4. The intelligent monitoring and early warning method for warehouse environment based on the Internet of Things according to claim 3, characterized in that, The construction of the risk assessment model in step S3 is specifically as follows: S301: Construct a dynamic risk quantification index based on the aforementioned anomaly source, mathematically described as follows: ,in, As a dynamic risk quantification indicator, Weighting based on the value of goods. Let be the vulnerability function of the goods. Due to deviations in environmental parameters, The safety deviation threshold for environmental parameters, Time weighting; The dynamic risk heatmap is generated based on the dynamic risk quantification index.

5. The method for intelligent monitoring and early warning of warehouse environment based on the Internet of Things according to claim 4, characterized in that, The simulation of the contingency plan in step S4 specifically refers to: Early warning information is generated based on the dynamic risk quantification indicators described in the dynamic risk heatmap; Multiple contingency plans are preset, and the net effect of each plan is simulated in the digital twin. Mathematically, this can be described as... ,in, For the net effect of plan P, To determine the risk value at position x before implementing the contingency plan P, To determine the risk value at position x after implementing contingency plan P, This is the penalty coefficient for side effects. The side effects of plan P at position k; The optimal contingency plan instruction set is output based on the net effect.

6. An intelligent monitoring and early warning system for warehouse environment based on the Internet of Things, characterized in that, The system is applied to the IoT-based intelligent monitoring and early warning method for warehouse environment as described in any one of claims 1-5, including a disturbance extraction module, a reverse tracing module, a risk assessment module, and a contingency plan simulation module; The disturbance extraction module is used to collect raw data packets of the storage environment and detect and extract disturbance signals; The reverse tracing module is used to construct a physical field back propagation model based on the disturbance signal and separate the source of the anomaly. The risk assessment module is used to construct a risk assessment model based on the anomaly source and generate a dynamic risk heat map. The contingency plan simulation module is used to simulate contingency plans based on the dynamic risk heat map and output the optimal contingency plan instruction set.

Images