Intelligent stereoscopic warehouse monitoring system

Abstract

The invention discloses an intelligent three-dimensional warehouse monitoring system, and relates to the technical field of intelligent storage automation, and the system comprises an early warning response module which is used for generating early warning signals of different levels according to a three-dimensional warehouse safety index, and triggering a corresponding control instruction; the control execution module is used for receiving the control instruction sent by the early warning response module and adjusting operation parameters of the environment adjusting equipment and the logistics equipment in the stereoscopic warehouse. According to the method, the specific calculation formulas of the environment risk coefficient, the equipment health coefficient and the inventory abnormity coefficient are designed, the stereoscopic warehouse safety evaluation model is constructed based on the three coefficients, the abstract stereoscopic warehouse safety state is converted into a quantifiable and comparable numerical value, a traditional subjective judgment mode is replaced, objective and accurate evaluation of the stereoscopic warehouse safety level is achieved, and the stereoscopic warehouse safety evaluation efficiency is improved. And potential safety hazards can be quickly and accurately identified.

Description

Technical Field

[0001] This invention relates to the field of intelligent warehouse automation technology, and in particular to an intelligent automated warehouse monitoring system. Background Technology

[0002] With the rapid upgrading of modern logistics and intelligent manufacturing industries, automated warehouses (AS / RS), as core infrastructure for high-density storage and efficient turnover of goods, are seeing their application scale continuously expand in e-commerce retail, auto parts, and pharmaceutical cold chain industries. Their operational efficiency, storage security, and operational stability have become key factors affecting the efficiency of supply chain circulation. Especially in scenarios involving centralized management of multiple categories of goods and high-volume storage and retrieval, AS / RS need to support higher storage density, meet the stringent requirements of pharmaceuticals and food for temperature, humidity, and harmful gases, and cope with the reliability demands of high-load operation of stacker cranes, conveyors, and elevators. Traditional manual inspection and single-point monitoring models are no longer suitable for the real-time and precise control of intelligent AS / RS, making the construction of multi-dimensional intelligent monitoring systems an inevitable trend in the industry.

[0003] Currently, automated warehouse monitoring technology has evolved from manual management to a preliminary stage of automation. Early traditional automated warehouses relied on manual inspections to record temperature and humidity, visual observation of equipment status, and manual inventory checks, which suffered from low data frequency, poor real-time performance, and large errors. In recent years, some automated warehouses have introduced sensors to achieve partial automation, such as using temperature and humidity sensors to collect environmental data, vibration sensors to monitor stacker crane status, and barcode scanning to count inventory. However, these technologies are mostly limited to a single dimension or device, lacking system integration. Environmental monitoring ignores the impact of volatile organic compounds on special goods, equipment monitoring only provides simple threshold alarms without multi-parameter health assessments, and inventory monitoring lacks the ability to identify packaging damage and surface contamination. Furthermore, the data is stored in a scattered manner, making it impossible to form a linkage analysis and support the overall safety assessment of the automated warehouse.

[0004] From a practical application perspective, existing monitoring technologies still have many unresolved issues. Firstly, environmental monitoring dimensions are incomplete, and early warnings are delayed. Most systems do not include volatile organic compound (VOC) monitoring and struggle to capture real-time temperature and humidity change rates, making goods susceptible to damage due to sudden parameter changes. Secondly, equipment monitoring lacks predictive capabilities, relying solely on vibration and noise threshold alarms without establishing health coefficient models. This makes it difficult to identify potential faults in advance, such as slow excessive vertical vibration of stacker cranes or vibration changes caused by conveyor belt wear. Maintenance is often reactive, increasing costs and disrupting operations. Thirdly, inventory monitoring lacks precision and dimensionality. Manual or barcode-based inventory checks are prone to errors, and there is a lack of methods to identify packaging damage and contamination areas. There is no real-time mechanism to compare actual and expected inventory, easily leading to stockpiling, shortages, or unresolved damaged goods. Fourthly, multi-dimensional data is fragmented, lacking comprehensive evaluation and a unified safety model for integrated analysis. This makes it difficult to output an overall safety index for automated warehouses, resulting in poor early warning and control linkages and hindering timely intervention, thus exacerbating operational safety hazards.

[0005] Therefore, it is imperative to invent an intelligent warehouse monitoring system to solve the above problems. Summary of the Invention

[0006] The purpose of this invention is to provide an intelligent automated warehouse monitoring system to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an intelligent warehouse monitoring system, comprising the following modules: The environmental monitoring module collects environmental status data through temperature and humidity sensors and gas concentration sensors deployed in the automated warehouse, forming an environmental monitoring dataset; the environmental monitoring dataset includes temperature distribution data, humidity distribution data, and gas concentration data; The equipment operation monitoring module collects mechanical vibration data through vibration and noise sensors installed on stacker cranes, conveyors, and elevators, forming an equipment operation monitoring dataset; the equipment operation monitoring dataset includes stacker crane vibration data, conveyor vibration data, and elevator noise data; The inventory status monitoring module collects goods storage data through RFID readers and image recognition devices to form an inventory status monitoring dataset; the inventory status monitoring dataset includes goods quantity data and goods appearance data. The data analysis module is used to analyze environmental monitoring datasets, equipment operation monitoring datasets, and inventory status monitoring datasets to obtain environmental risk coefficients, equipment health coefficients, and inventory anomaly coefficients. The environmental risk coefficients, equipment health coefficients, and inventory anomaly coefficients are then input into the automated warehouse safety assessment model to output the automated warehouse safety index. The early warning response module is used to generate early warning signals of different levels based on the safety index of the automated warehouse and trigger corresponding control commands; The control execution module is used to receive control commands from the early warning response module and adjust the operating parameters of the environmental control equipment and logistics equipment in the automated warehouse. The data storage and management module is used to store environmental monitoring datasets, equipment operation monitoring datasets, inventory status monitoring datasets, automated warehouse safety indices and historical early warning records, and provides data query and analysis interfaces.

[0008] Preferably, the temperature distribution data includes the rate of temperature change; the humidity distribution data includes the rate of humidity change; and the gas concentration data includes the concentration of volatile organic compounds.

[0009] Preferably, the stacker vibration data includes the vertical vibration amplitude of the stacker; the conveyor vibration data includes the vibration amplitude of the conveyor belt; and the hoist noise data includes the decibel value of the hoist operating noise.

[0010] Preferably, the quantity data of the goods includes the actual inventory quantity and the expected inventory quantity; the appearance data of the goods includes the degree of packaging damage and the percentage of surface contamination area.

[0011] Preferably, the formula for calculating the environmental risk coefficient is: , Where ΔT is the rate of temperature change, T max To represent the maximum permissible rate of temperature change, ΔH represents the rate of humidity change, H max To allow the maximum rate of humidity change, G voc G represents the concentration of volatile organic compounds. std Let be the threshold for volatile organic compound concentration, e be the natural constant, and α, β, and γ be weighting factors that satisfy α+β+γ=1.

[0012] Preferably, the formula for calculating the health coefficient of the equipment is: , Among them, V s V represents the vertical vibration amplitude of the stacker crane. s，max V is the maximum allowable vertical vibration amplitude of the stacker crane. c V represents the vibration amplitude of the conveyor belt. c，max N represents the maximum allowable belt vibration amplitude of the conveyor. d The noise level of the hoist in decibels, N d，max This is the maximum permissible noise level in decibels for the hoist.

[0013] Preferably, the formula for calculating the inventory anomaly coefficient is: , Among them, Q a Q represents the actual inventory quantity. e D represents the expected inventory quantity. p D represents the degree of packaging damage. p，max To maximize the permissible level of packaging damage, S d S represents the percentage of surface contamination area. d，max The maximum allowable percentage of surface area contaminated is represented by max, which is a function representing the maximum value.

[0014] Preferably, the calculation formula for the automated warehouse safety assessment model is as follows: , Among them, I s For the safety index of automated warehouses, C e C represents the environmental risk coefficient. d For the equipment health coefficient, C i This is the inventory anomaly coefficient.

[0015] Preferably, the warning signals include a first-level warning signal, a second-level warning signal, and a third-level warning signal; Preferably, the adjustment process of the control execution module is as follows: Receive control commands issued by the early warning response module; If the instruction corresponds to a level-two warning signal, then adjust the operating parameters of the environmental control equipment, including: starting the ventilation system in the designated area and setting the target temperature to T. target The target humidity is H target Reduce the operating speed of related logistics equipment to δ times the rated speed, where 0 < δ < 1; If the instruction corresponds to a Level 3 warning signal, then adjust the operating parameters of the environmental control equipment and logistics equipment, including: activating the emergency ventilation and air purification system throughout the warehouse area; and forcibly stopping the operation of the health coefficient C. d Below the threshold D th The equipment operation; the health coefficient C d Above the threshold D th The device is switched to a low-speed safety mode, with the operating speed limited to ε times the rated speed, where 0 < ε < δ.

[0016] The technical effects and advantages of this invention are as follows: 1. This invention, by deploying an environmental monitoring module, an equipment operation monitoring module, and an inventory status monitoring module, collects environmental, equipment, and inventory data of the automated warehouse from multiple dimensions and forms corresponding datasets. This breaks through the limitations of traditional single-dimensional monitoring and achieves comprehensive and seamless control over the overall operation status of the automated warehouse, laying a comprehensive data foundation for subsequent safety assessments. 2. This invention designs specific calculation formulas for environmental risk coefficient, equipment health coefficient, and inventory anomaly coefficient, and constructs an automated warehouse safety assessment model based on these three factors. This transforms the abstract automated warehouse safety status into quantifiable and comparable values, replacing the traditional subjective judgment mode, and achieving an objective and accurate assessment of the safety level of the automated warehouse. It can quickly and accurately identify potential safety hazards. 3. This invention divides early warning signals into three levels: Level 1, Level 2, and Level 3, and matches differentiated control strategies to different early warning levels. For example, Level 2 early warning can activate ventilation in designated areas and reduce the speed of logistics equipment, while Level 3 early warning can activate emergency ventilation in the entire warehouse area, forcibly stop high-risk equipment, or switch to a low-speed mode. This achieves graded early warning and precise control, which can avoid excessive intervention under low-risk conditions that affects operational efficiency, and prevent insufficient response under high-risk conditions that leads to increased losses. Attached Figure Description

[0017] Figure 1 This is a system framework diagram of the present invention.

[0018] Figure 2 This is a schematic diagram of the module execution flow of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] This invention provides, for example Figure 1 The intelligent warehouse monitoring system shown includes the following modules: environmental monitoring module, equipment operation monitoring module, inventory status monitoring module, data analysis module, early warning response module, control execution module, and data storage and management module.

[0021] This invention provides, for example Figure 2 The module execution flow diagram shown is as follows: The environmental monitoring module collects environmental status data through temperature and humidity sensors and gas concentration sensors deployed in the automated warehouse, forming an environmental monitoring dataset; the environmental monitoring dataset includes temperature distribution data, humidity distribution data, and gas concentration data; It should be noted that the temperature and humidity sensor is an integrated temperature and humidity composite sensor with digital signal output, covering a temperature range of -40℃ to 85℃ and a relative humidity range of 0% to 100%, with an accuracy of ±0.5℃ for temperature and ±3%RH for humidity. Furthermore, in the above technical solution, the temperature distribution data includes the rate of temperature change; the humidity distribution data includes the rate of humidity change; and the gas concentration data includes the concentration of volatile organic compounds.

[0022] It should be noted that the temperature change rate is acquired in real time by integrated temperature and humidity composite sensors with digital signal output deployed in various functional areas of the automated warehouse. The sensors continuously measure the ambient temperature value at a fixed sampling interval Δt = 10 seconds, and record the temperature measurement values ​​T1, T2, ..., T in time series in the data storage and management module. n The instantaneous rate of change is calculated using the differential calculation module: obtaining the adjacent sampling time t. k With t k+1 Temperature value T k and T k+1 According to the formula ΔT=∣T k+1 -T k | / Δt calculates the temperature change per unit time, where Δt = t k+1 -t k =10 seconds, and the final output is a data stream of temperature change rate with timestamps; The humidity change rate is measured using a digital temperature and humidity composite sensor integrated with temperature monitoring. Sampling is performed within the relative humidity range of 0% to 100% with an accuracy of ±3%RH. Humidity measurements H1, H2, ..., H are acquired at intervals of Δt = 10 seconds. n The real-time data processing unit performs time-series difference operations on the continuously sampled values ​​to extract adjacent time points t. m Humidity value H m With t m+1 Humidity value H m+1 According to the preset algorithm ΔH=|H m+1 -H m | / Δt calculates the rate of change of humidity per unit time, where the time step Δt is fixed at 10 seconds, and the calculation results are synchronously transmitted to the environmental monitoring dataset. The concentration of volatile organic compounds (VOCs) is collected using semiconductor gas sensors distributed 1.5 meters above the ground in the shelving area. The sensors have a range of 0-1000 ppm and a detection resolution of 0.1 ppm. A gas sampling cycle is performed every 5 minutes: the sensor probe actively draws in air samples from the storage area, and the built-in catalytic combustion unit converts the VOC components into quantifiable electrical signals. The A / D conversion module outputs a standard 4-20mA analog signal, which is then converted into a digital concentration value G with 16-bit precision by the data acquisition card. voc Finally, the time series data of volatile organic compound concentrations are stored according to the region number.

[0023] The equipment operation monitoring module collects mechanical vibration data through vibration and noise sensors installed on stacker cranes, conveyors, and elevators, forming an equipment operation monitoring dataset; the equipment operation monitoring dataset includes stacker crane vibration data, conveyor vibration data, and elevator noise data; It should be noted that the vibration sensor includes a piezoelectric accelerometer and a capacitive micro-vibration sensor, with a frequency response range of not less than 0.5Hz to 2000Hz and a dynamic range of not less than 80dB. Furthermore, in the above technical solution, the stacker vibration data includes the vertical vibration amplitude of the stacker; the conveyor vibration data includes the vibration amplitude of the conveyor belt; and the elevator noise data includes the decibel value of the elevator's operating noise.

[0024] It should be noted that the vertical vibration amplitude of the stacker crane is acquired by a triaxial piezoelectric accelerometer mounted on the base of the stacker crane's drive motor. The sensor has a range of ±20g, a frequency response of 0.5Hz-2000Hz, and a sampling rate of 1kHz. The sensor's Z-axis (vertical) output signal is filtered by a 4kHz low-pass filter and then subjected to a second integration operation by an integrator: the time-domain acceleration signal a... z (t) converted to displacement And extract the peak displacement V within a 10ms time window. s =max∣d z (t)| is used as the vertical vibration amplitude, with a measurement resolution of 0.01 mm; The vibration amplitude of the conveyor belt was acquired using a non-contact laser vibration meter. The meter was installed 0.5m above the belt surface on the conveyor support, emitting a 650nm wavelength laser beam and capturing the belt surface displacement at a 1MHz sampling rate. The original displacement signal s(t) was filtered by a 100Hz high-pass filter to eliminate belt sag interference, and then the vibration components were extracted through time-domain analysis: the peak-to-peak value V was calculated within a 1s period. c =max[s(t)]-min[s(t)], measurement range 0-30mm, accuracy ±0.1%FS; The decibel value of the hoist's operating noise is collected by an explosion-proof sound pressure sensor. The sensor is installed 1m away from the hoist drive unit and equipped with a 1 / 2-inch pre-polarized microphone with a frequency range of 20Hz-12.5kHz. After the sound pressure signal is filtered by an A-weighted network, the effective value within a 200ms time window is calculated by an RMS detector and finally converted into a decibel value with a dynamic range of 30dB-130dB.

[0025] The inventory status monitoring module collects goods storage data through RFID readers and image recognition devices to form an inventory status monitoring dataset; the inventory status monitoring dataset includes goods quantity data and goods appearance data. It should be noted that the image recognition device includes a high-resolution industrial camera based on a CMOS image sensor and an infrared thermal imaging camera, with a resolution of not less than 1920×1080 pixels, a frame rate of not less than 30fps, and equipped with an adaptive optical zoom lens. Furthermore, in the above technical solution, the quantity data of goods includes the actual inventory quantity and the expected inventory quantity; the appearance data of goods includes the degree of packaging damage and the percentage of surface contamination area.

[0026] It's important to know that the actual inventory quantity is collected through a fixed RFID reader array deployed in the rack aisles. The readers operate at a frequency of 902-928MHz with a transmission power of 30dBm, and the location tags are activated simultaneously during stacker crane operations. The system uses a time-slotted ALOHA anti-collision algorithm to identify valid tags in real time, count the quantity of goods per location, and finally summarize the total actual inventory Q for the warehouse area. a ; The expected inventory quantity is obtained in real time from the warehouse management system via the OPC UA protocol. The system polls the data table of the warehouse management system database every 30 seconds, extracts the planned storage quantity of each storage location, and calculates the total expected inventory Qe by storage area after the data verification module verifies the consistency of the timestamp. The data interface transmission delay is ≤100ms. The extent of packaging damage was assessed using a high-resolution industrial camera equipped with a 20-megapixel CMOS sensor. The camera was mounted at a 45-degree angle 1.2 meters above the conveyor, using a 200W LED array light source. Image acquisition was triggered when goods passed through the detection area. The packaging outline was extracted using the Mask R-CNN instance segmentation algorithm, and the pixel area A of the damaged region was calculated. d With total packaging area A t Degree of damage D p =A d / A t The detection resolution reaches 0.1mm. 2 / pixel, detection speed ≤1s / piece; The percentage of surface contamination area was acquired using a multispectral imaging system, which includes a visible light camera (400-700nm) and a near-infrared camera (900-1700nm), combined with a laser 3D scanner with 0.1mm precision. Spectral reflectance analysis was performed on the cargo surface to identify the pixel coordinate set Ω of the contaminated area. c The actual polluted surface area was calculated by reconstructing the three-dimensional point cloud. The data analysis module is used to analyze environmental monitoring datasets, equipment operation monitoring datasets, and inventory status monitoring datasets to obtain environmental risk coefficients, equipment health coefficients, and inventory anomaly coefficients. The environmental risk coefficients, equipment health coefficients, and inventory anomaly coefficients are then input into the automated warehouse safety assessment model to output the automated warehouse safety index. Furthermore, in the above technical solution, the formula for calculating the environmental risk coefficient is: , Where ΔT is the rate of temperature change, T max To represent the maximum permissible rate of temperature change, ΔH represents the rate of humidity change, H max To allow the maximum rate of humidity change, G voc G represents the concentration of volatile organic compounds. std Let be the threshold for volatile organic compound concentration, e be the natural constant, and α, β, and γ be weighting factors that satisfy α+β+γ=1.

[0027] It is important to know that the weighting factors α, β, and γ are specifically set as follows: based on the statistical analysis of N groups of valid samples from a historical environmental anomaly event database, the frequency f of temperature mutation events, humidity mutation events, and VOC exceedance events is extracted. T fH f G According to the formula , , Calculate the initial weights and manually fine-tune them with a precision of 0.01 through the management interface under the constraints 0.3≤α, β and γ≤0.5 and α+β+γ=1, where N≥1000. The temperature abrupt change event is defined as the temperature change rate ΔT being detected within three consecutive sampling periods Δt that satisfies the following condition. ≥0.9, and cumulative temperature change amplitude When the temperature is ≥5℃, it is determined to be a temperature change event, where Δt = 10 seconds; The humidity abrupt change event is defined as the humidity change rate ΔH satisfying the following condition within 6 consecutive sampling periods Δt: ≥0.85, and cumulative humidity change When the RH is ≥15%, it is determined to be a humidity change event, where Δt = 10 seconds; The VOC exceeding the standard event is when the volatile organic compound concentration G voc Two consecutive samples satisfy G voc >0.95×G std Or a single sample value G voc ≥1.2×G std When the sampling interval is 5 minutes, it is determined to be a VOC exceeding the standard event; The maximum allowable temperature change rate T max =3℃ / min; The maximum allowable humidity change rate H max =20%RH / min; The volatile organic compound concentration threshold G std =100ppm.

[0028] Furthermore, in the above technical solution, the formula for calculating the equipment health coefficient is: , Among them, V s V represents the vertical vibration amplitude of the stacker crane. s，max V is the maximum allowable vertical vibration amplitude of the stacker crane. c V represents the vibration amplitude of the conveyor belt. c，max N represents the maximum allowable belt vibration amplitude of the conveyor. d The noise level of the hoist in decibels, N d，max This is the maximum permissible noise level in decibels for the hoist.

[0029] It should be noted that the stacker crane is allowed a maximum vertical vibration amplitude V. s，max The maximum allowable belt vibration amplitude V of the conveyor c，maxThe maximum permissible noise level N for the hoist d，max The maximum permissible vertical vibration amplitude V of the stacker crane, conveyor, and elevator is determined according to the manufacturer's technical documentation. s，max Depending on the equipment model and installation foundation (e.g., concrete structure), typical values ​​range from 0.5mm to 2mm; specific values ​​should be consulted in the equipment manual. The maximum allowable belt vibration amplitude V of the conveyor... c，max Depending on the belt type and load, typical values ​​range from 1mm to 5mm; the maximum permissible noise level for the hoist is N. d，max Typical values ​​are between 75dB and 85dB.

[0030] Furthermore, in the above technical solution, the formula for calculating the inventory anomaly coefficient is: , Among them, Q a Q represents the actual inventory quantity. e D represents the expected inventory quantity. p D represents the degree of packaging damage. p，max To maximize the permissible level of packaging damage, S d S represents the percentage of surface contamination area. d，max The maximum allowable percentage of surface area contaminated is represented by max, which is a function representing the maximum value.

[0031] It is important to know that the maximum permissible level of packaging damage, D... p，max and the maximum allowable surface contamination area percentage S d，max The value is set to D p，max =5%, S d，max =1%, where the maximum permissible level of packaging damage is D. p，max The value is set to 5%, which conforms to the definition of "acceptable quality level" in common quality standards such as ISO 9001 and ASTM D4169. This allows for minor scratches or dents on the goods without affecting their core functions. It also incorporates the patented system's high-precision image detection capability of 0.1mm² / pixel, ensuring accurate identification of small-area damage. The maximum permissible surface contamination area percentage, S... d，max The value is set to 1%, which refers to the hygiene requirements of GMP and HACCP for food and pharmaceutical storage. The multispectral imaging system is used to achieve highly sensitive monitoring of the contaminated area and avoid the risk of cross-contamination.

[0032] Furthermore, in the above technical solution, the calculation formula for the safety assessment model of the automated warehouse is: , Among them, I s For the safety index of automated warehouses, C e C represents the environmental risk coefficient. d For the equipment health coefficient, Ci This is the inventory anomaly coefficient.

[0033] The early warning response module is used to generate early warning signals of different levels based on the safety index of the automated warehouse and trigger corresponding control commands; Furthermore, in the above technical solution, the warning signal includes a first-level warning signal, a second-level warning signal, and a third-level warning signal; It should be noted that when the safety index of the automated warehouse meets condition I... s When the value is ≥0.8, a Level 1 warning signal is generated. This signal is green, indicating that the system is in normal condition, and only a normal condition prompt message is sent to the monitoring center. When the safety index of the automated warehouse meets the condition 0.6≤I s When the value is less than 0.8, a level 2 warning signal is generated. This signal is yellow and indicates that the system has a slight anomaly. A warning notification is sent to the monitoring center and equipment maintenance personnel, prompting them to check the equipment and adjust the environmental parameters. When the safety index of the automated warehouse meets condition I s When the value is less than 0.6, a Level 3 warning signal is generated. This signal is red and indicates that there is a serious risk in the system. An emergency alarm is sent to the monitoring center, equipment maintenance personnel and safety management personnel, and the equipment degraded operation mode and environmental forced adjustment program are automatically triggered.

[0034] The control execution module is used to receive control commands from the early warning response module and adjust the operating parameters of the environmental control equipment and logistics equipment in the automated warehouse. Furthermore, in the above technical solution, the adjustment process of the control execution module is as follows: Receive control commands issued by the early warning response module; If the instruction corresponds to a level-two warning signal, then adjust the operating parameters of the environmental control equipment, including: starting the ventilation system in the designated area and setting the target temperature to T. target The target humidity is H target Reduce the operating speed of related logistics equipment to δ times the rated speed, where 0 < δ < 1; If the instruction corresponds to a Level 3 warning signal, then adjust the operating parameters of the environmental control equipment and logistics equipment, including: activating the emergency ventilation and air purification system throughout the warehouse area; and forcibly stopping the operation of the health coefficient C. d Below the threshold D th The equipment operation; the health coefficient C d Above the threshold D th The device is switched to a low-speed safety mode, with the operating speed limited to ε times the rated speed, where 0 < ε < δ.

[0035] It is important to know that the typical value for δ is set to 0.8, and the typical value for ε is set to 0.5. In one specific implementation, when the early warning response module generates a level-two early warning signal, i.e., a yellow alert, and the comprehensive index is between 0.6 and 0.8, the control execution module will initiate a graded control program. This program first adjusts the environment, activating the intelligent ventilation system in the abnormal area, setting the target temperature to 22 degrees Celsius, allowing a fluctuation of ±0.5 degrees Celsius (a 3-degree Celsius adjustment from the current temperature), and simultaneously controlling the target humidity at 45% relative humidity, allowing a fluctuation of ±3%. Secondly, it limits the speed of equipment, reducing the operating speed of related logistics equipment such as stacker cranes and conveyors to 0.8 times their rated speed, a reduction of 20%. For example, the horizontal operating speed of a stacker crane will be reduced from 180 meters per minute to 144 meters per minute, and the conveyor belt speed from 60 meters per minute to 48 meters per minute. When the warning is upgraded to a Level III warning signal, i.e., a red alert, and the comprehensive index is below 0.6, the system will implement enhanced intervention strategies. First, it will activate comprehensive environmental control, turning on the emergency ventilation and air purification systems throughout the entire storage area to force the concentration of volatile organic compounds to drop below 100 ppm within 15 minutes. Second, it will implement tiered equipment management. Equipment with a health coefficient below 0.7 will be immediately shut down, such as a stacker crane with excessive vibration. Equipment with a health coefficient of 0.7 or higher will be switched to a low-speed safety mode, limiting its operating speed to half of its rated speed. For example, the lifting speed of the hoist will be limited from 30 meters per minute to 15 meters per minute, and the conveyor belt speed will be further reduced to 24 meters per minute. The speed limit in this low-speed safety mode will always be lower than the speed limit standard during a Level II warning.

[0036] The data storage and management module is used to store environmental monitoring datasets, equipment operation monitoring datasets, inventory status monitoring datasets, automated warehouse safety indices and historical early warning records, and provides data query and analysis interfaces.

[0037] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent automated warehouse monitoring system, characterized in that, Includes the following modules: The environmental monitoring module collects environmental status data through temperature and humidity sensors and gas concentration sensors deployed in the automated warehouse, forming an environmental monitoring dataset; the environmental monitoring dataset includes temperature distribution data, humidity distribution data, and gas concentration data; The equipment operation monitoring module collects mechanical vibration data through vibration and noise sensors installed on stacker cranes, conveyors, and elevators, forming an equipment operation monitoring dataset; the equipment operation monitoring dataset includes stacker crane vibration data, conveyor vibration data, and elevator noise data; The inventory status monitoring module collects goods storage data through RFID readers and image recognition devices to form an inventory status monitoring dataset; the inventory status monitoring dataset includes goods quantity data and goods appearance data. The data analysis module is used to analyze environmental monitoring datasets, equipment operation monitoring datasets, and inventory status monitoring datasets to obtain environmental risk coefficients, equipment health coefficients, and inventory anomaly coefficients. These coefficients are then input into the automated warehouse safety assessment model to output the automated warehouse safety index. The early warning response module is used to generate early warning signals of different levels based on the safety index of the automated warehouse and trigger corresponding control commands; The control execution module is used to receive control commands from the early warning response module and adjust the operating parameters of the environmental control equipment and logistics equipment in the automated warehouse. The data storage and management module is used to store environmental monitoring datasets, equipment operation monitoring datasets, inventory status monitoring datasets, automated warehouse safety indices and historical early warning records, and provides data query and analysis interfaces.

2. The intelligent warehouse monitoring system according to claim 1, characterized in that, The temperature distribution data includes the rate of temperature change; the humidity distribution data includes the rate of humidity change; and the gas concentration data includes the concentration of volatile organic compounds.

3. The intelligent warehouse monitoring system according to claim 1, characterized in that, The stacker vibration data includes the vertical vibration amplitude of the stacker; the conveyor vibration data includes the vibration amplitude of the conveyor belt; and the elevator noise data includes the decibel value of the elevator's operating noise.

4. The intelligent warehouse monitoring system according to claim 1, characterized in that, The quantity data of the goods includes the actual inventory quantity and the expected inventory quantity; the appearance data of the goods includes the degree of packaging damage and the percentage of surface contamination area.

5. The intelligent warehouse monitoring system according to claim 1, characterized in that, The formula for calculating the environmental risk coefficient is as follows: ， Where ΔT is the rate of temperature change, T max To represent the maximum permissible rate of temperature change, ΔH represents the rate of humidity change, H max To allow the maximum rate of humidity change, G voc G represents the concentration of volatile organic compounds. std Let be the threshold for volatile organic compound concentration, e be the natural constant, and α, β, and γ be weighting factors that satisfy α+β+γ=1.

6. The intelligent warehouse monitoring system according to claim 1, characterized in that, The formula for calculating the health coefficient of the equipment is as follows: ， Among them, V s V represents the vertical vibration amplitude of the stacker crane. s，max V is the maximum allowable vertical vibration amplitude of the stacker crane. c V represents the vibration amplitude of the conveyor belt. c，max N represents the maximum allowable belt vibration amplitude of the conveyor. d The noise level of the hoist in decibels, N d，max This is the maximum permissible noise level in decibels for the hoist.

7. The intelligent automated warehouse monitoring system according to claim 1, characterized in that, The formula for calculating the inventory anomaly coefficient is as follows: ， Among them, Q a Q represents the actual inventory quantity. e D represents the expected inventory quantity. p D represents the degree of packaging damage. p，max To maximize the permissible level of packaging damage, S d S represents the percentage of surface contamination area. d，max The maximum allowable percentage of surface area contaminated is represented by max, which is a function representing the maximum value.

8. The intelligent warehouse monitoring system according to claim 1, characterized in that, The calculation formula for the safety assessment model of the automated warehouse is as follows: ， Among them, I s For the safety index of automated warehouses, C e C represents the environmental risk coefficient. d For the equipment health coefficient, C i This is the inventory anomaly coefficient.

9. The intelligent automated warehouse monitoring system according to claim 1, characterized in that, The warning signals include Level 1 warning signals, Level 2 warning signals, and Level 3 warning signals.

10. The intelligent warehouse monitoring system according to claim 1, characterized in that, The adjustment process of the control execution module is as follows: Receive control commands issued by the early warning response module; If the instruction corresponds to a level-two warning signal, then adjust the operating parameters of the environmental control equipment, including: starting the ventilation system in the designated area and setting the target temperature to T. target The target humidity is H target Reduce the operating speed of related logistics equipment to δ times the rated speed, where 0 < δ < 1; If the instruction corresponds to a Level 3 warning signal, then adjust the operating parameters of the environmental control equipment and logistics equipment, including: activating the emergency ventilation and air purification system throughout the warehouse area; and forcibly stopping the operation of the health coefficient C. d Below the threshold D th The equipment operation; the health coefficient C d Above the threshold D th The device is switched to a low-speed safety mode, with the operating speed limited to ε times the rated speed, where 0 < ε < δ.

Images