Fermentation ground cylinder backfill soil monitoring system based on sensor network

Abstract

The invention relates to the technical field of sensor monitoring, in particular to a fermentation ground cylinder backfill monitoring system based on a sensor network, which comprises a temperature and humidity prediction module, a communication optimization module, a data acquisition module, an anomaly detection module and a leakage monitoring module. According to the invention, by analyzing microbial metabolism characteristics, identifying temperature and humidity references in the fermentation process, providing a data basis for abnormal data detection and optimizing a data flow path, the communication stability and the energy efficiency ratio are improved, the data transmission delay is reduced, the data acquisition frequency is dynamically adjusted, and a fine data acquisition strategy is realized; the accuracy and the real-time performance of data acquisition are optimized, the temperature gradient change rate and the gas concentration change trend are calculated, the humidity state of backfill soil is combined, the accuracy of anomaly detection is enhanced, false alarm and missing alarm are reduced, leakage is detected in real time by recognizing a gas diffusion path, and the accuracy and the quick response capability of leakage monitoring are improved. And the comprehensive performance and applicability of the monitoring system are improved.

Description

Technical Field

[0001] The invention relates to the field of sensor monitoring technology, and in particular to a fermentation tank backfill soil monitoring system based on a sensor network. Background Art

[0002] The field of sensor monitoring technology includes technologies for real-time monitoring, collection and processing of physical, chemical, biological and other environmental parameters based on various sensor devices. The core content includes data collection, signal conversion, data transmission and analysis and processing, and is applied to industrial automation, environmental monitoring, and intelligent manufacturing. In the industrial production process, sensor monitoring technology is used to detect temperature, humidity, pressure, gas composition, liquid level and other key parameters to ensure the stability of the production environment and improve the accuracy of process control. With the improvement of sensor accuracy and the development of wireless communication technology, monitoring systems based on sensor networks have become an important support for intelligent manufacturing and refined management. Through remote monitoring, automatic control, and multi-sensor fusion data processing, the reliability and real-time performance of the monitoring system are improved.

[0003] Among them, the fermentation tank backfill soil monitoring system based on the sensor network refers to the use of multiple types of sensors to collect the temperature, humidity, and gas composition data of the fermentation tank backfill soil, and send the monitoring data to the central processing system for analysis and storage through wireless transmission technology. The system covers wireless temperature and humidity sensors, gas detection sensors, data acquisition modules, low-power wireless communication modules, and remote monitoring terminals to form a complete monitoring network. The monitoring system periodically collects environmental parameters in the backfill soil through distributed sensor nodes, and uses edge computing technology to pre-process the data locally, and then transmits it to the data management platform using a wireless network. On the data management platform, the data undergoes multi-channel filtering to reduce environmental noise interference, and uses a threshold setting method for abnormal state detection to facilitate real-time monitoring and early warning. The system uses a low-power communication protocol to reduce energy consumption, and combines data storage management technology to achieve archiving and historical analysis of long-term monitoring data, providing data support for the fermentation process.

[0004] Traditional fermentation tank backfill soil monitoring technology relies on a fixed collection frequency for data collection and fails to make dynamic adjustments according to different environmental change conditions, resulting in a lag in data collection when environmental parameters change rapidly and unnecessary data redundancy when the environment is stable, which reduces the efficiency of data collection. The data transmission path depends on the preset network structure and cannot be optimized and adjusted in combination with the real-time signal quality and energy consumption. As a result, nodes with high energy consumption or severe signal attenuation are overloaded, affecting the stability of data transmission. In terms of anomaly detection, it relies on a single threshold setting for state judgment, and does not fully consider the influence of temperature and humidity change trends and soil moisture on gas diffusion, resulting in a high false alarm rate in the detection of abnormal states, reducing the reliability of the system. In terms of gas leakage monitoring, the gas diffusion path information is not fully utilized for leakage risk assessment, and judgment is only based on single-point concentration changes, resulting in limited leakage identification capabilities in complex environments, leading to misjudgment or missed judgment, affecting the overall performance of the monitoring system. In actual applications, it may cause data lag, unstable transmission, inaccurate anomaly detection, and untimely leakage monitoring response, reducing the reliability and practicality of the monitoring system in industrial production and environmental monitoring. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a fermentation tank backfill soil monitoring system based on a sensor network.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A fermentation tank backfill soil monitoring system based on a sensor network comprises: The temperature and humidity prediction module obtains microbial metabolic characteristic data, calculates the metabolic heat release rate and water vapor release rate in multiple fermentation stages, analyzes the temperature and humidity change characteristics, and establishes a temperature and humidity benchmark prediction model; The communication optimization module calls the temperature and humidity benchmark prediction model to obtain the geographical location, wireless signal strength, and energy consumption level of the sensor node, and adjusts and optimizes the data flow path by calculating the cost and signal quality of data transmission between nodes to generate an optimized communication path; The data acquisition module calls the optimized communication path and uses sensors to obtain the temperature and humidity data of the backfill soil and the concentration data of various gases in real time, and adjusts the data acquisition frequency of the sensor by analyzing the rate of change of the data to obtain the acquisition frequency parameters; The anomaly detection module uses the acquisition frequency parameters to calculate the temperature gradient change rate and gas concentration change trend of multiple regions in real time, combines the backfill soil moisture status, analyzes and detects abnormal heat diffusion paths, and generates heat transfer anomaly judgment values.

[0007] As a further scheme of the present invention, the temperature and humidity benchmark prediction model specifically includes metabolic heat release rate, water vapor release rate, and temperature and humidity change trend; the optimized communication path includes data transmission cost, signal quality, and data flow path between nodes; the acquisition frequency parameters specifically include temperature and humidity data change rate, multiple gas concentration change rate, and sensor acquisition frequency adjustment value; the heat transfer anomaly judgment value includes temperature gradient change rate, gas concentration change trend, and abnormal heat diffusion path.

[0008] As a further solution of the present invention, the temperature and humidity prediction module includes: The metabolic heat calculation submodule obtains microbial metabolic characteristic data, including oxygen consumption rate and carbon dioxide release rate. According to the heat changes of oxygen consumption and carbon dioxide release, the formula is used: ; Calculate the metabolic heat release rate per unit volume to obtain the heat release rate; in, represents the metabolic heat release rate, represents the calorific value of oxygen combustion, Representative The oxygen consumption rate at a given moment is represents the calorific value of carbon dioxide combustion, Representative The carbon dioxide release rate at a given moment is represents the unit volume, represents the total number of time steps, represents the index of the time step; The water vapor release calculation submodule calls the heat release rate and calculates the water vapor release rate using the oxygen consumption rate and the carbon dioxide release rate; The temperature and humidity prediction modeling submodule calls the water vapor release rate, combines the heat release rate data of each fermentation stage, records the temperature and humidity change characteristics of multiple fermentation stages, and constructs a temperature and humidity benchmark prediction model.

[0009] As a further solution of the present invention, the communication optimization module includes: The data acquisition submodule calls the temperature and humidity benchmark prediction model to obtain the geographical location, wireless signal strength, and energy consumption level of the sensor node, and generates a node information data set; The signal quality analysis submodule calls the node information data set, analyzes and records the transmission cost and signal quality between multiple nodes, and generates a signal quality evaluation value; The path score calculation submodule uses the formula: ; Calculate the scores of multiple signal transmission paths, adjust and optimize the data flow path by comparing the scores of multiple paths, and generate an optimized communication path; in, represents the path score, represents the signal quality between the bth pair of nodes in the path, represents the transmission cost between the bth pair of nodes in the path, A weighting factor representing the signal quality, The weight factor representing the cost, represents the total number of node pairs in the path, Represents the index of a node pair in a path.

[0010] As a further solution of the present invention, the data acquisition module includes: The sensor data acquisition submodule calls the optimized communication path to obtain the temperature and humidity data of each sensor node and the concentration data of multiple gases to generate raw acquisition data; The change rate analysis submodule calls the original collected data, analyzes the change rate of the data according to the temperature and humidity data and gas concentration data collected by the sensor, evaluates the change trend, and generates the data change rate; The acquisition frequency adjustment submodule adopts the formula based on the data change rate: ; Calculate the acquisition frequency adjustment value, adjust the data acquisition frequency, and obtain the acquisition frequency parameters; in, represents the adjusted acquisition frequency, Represents the amount of data change, represents the time variation, represents the temperature change weight, represents the humidity change weight, Represents the weight of gas concentration change.

[0011] As a further solution of the present invention, the anomaly detection module includes: The temperature gradient calculation submodule uses the acquisition frequency parameters to obtain temperature data of multiple regions in real time, calculates the temperature difference between each region, identifies the speed and direction of heat diffusion in combination with the position coordinates, and obtains the temperature gradient change rate; The gas concentration trend analysis submodule calculates the change trend of multiple gas concentrations in each area in real time based on the temperature gradient change rate and the gas concentration data, analyzes the gas diffusion rate, and obtains the gas concentration trend offset; The heat transfer anomaly determination submodule adopts the formula based on the gas concentration trend offset and the measured value of backfill soil humidity: ; Calculate the heat diffusion path anomaly coefficient and generate the heat transfer anomaly judgment value; in, represents the heat diffusion path anomaly coefficient, Represents the gas concentration trend offset, represents the rate of change of temperature gradient, Represents the measured value of backfill soil moisture, represents the data collection time interval, Represents the absolute value of the humidity change rate.

[0012] As a further solution of the present invention, the system further includes: The leakage monitoring module calls the heat transfer anomaly judgment value, detects gas leakage in real time and generates leakage monitoring results by identifying and analyzing the diffusion path of the gas according to the real-time change rate of carbon dioxide and oxygen concentrations, combined with the porosity and real-time humidity state of the backfill soil; The leakage monitoring results specifically refer to the rate of change of carbon dioxide concentration, the rate of change of oxygen concentration, and the gas diffusion path.

[0013] As a further solution of the present invention, the leakage monitoring module includes: The gas diffusion resistance calculation submodule calls the heat transfer anomaly judgment value, combines the backfill soil porosity and real-time humidity status data, evaluates the degree of gas restriction, calculates the restriction of gas flow, evaluates the diffusion capacity of gas in multiple areas, and obtains gas diffusion resistance data; The gas flow direction determination submodule calls the gas diffusion resistance data, combines the gas concentration change trend data, calculates the diffusion gradient between multiple measuring points, compares the diffusion resistance of each area, analyzes the gas flow direction, and obtains the gas flow direction information; The leakage risk assessment submodule calls the gas flow direction information, combines the gas diffusion resistance data, identifies the distribution of gas in multiple areas, and uses the formula: ; Calculate the leakage risk index of each area, detect gas leakage, and generate leakage monitoring results; in, For the The leakage risk index of each region, For the In the region The target gas concentration at each measuring point is For the In the region The gas diffusion gradient at each measuring point is For the In the region The gas diffusion resistance at each measuring point is For the In the region Environmental impact factors of each measuring point, For Region The total number of measurement points within .

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by analyzing the metabolic characteristics of microorganisms and identifying the temperature and humidity benchmarks in the fermentation process, a data basis is provided for abnormal data detection, the data flow path is optimized, the stability and energy efficiency of communication are improved, the data transmission delay is reduced, the data acquisition frequency is dynamically adjusted, a sophisticated data acquisition strategy is implemented, the accuracy and real-time performance of data acquisition are optimized, the temperature gradient change rate and the gas concentration change trend are calculated, and the accuracy of anomaly detection is enhanced in combination with the humidity status of backfill soil, and false alarms and missed alarms are reduced. By identifying the gas diffusion path, leaks are detected in real time, the accuracy and rapid response capability of leak monitoring are improved, and the comprehensive performance and applicability of the monitoring system are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a system flow chart of the present invention; Figure 2 It is a flow chart of the temperature and humidity prediction module of the present invention; Figure 3 It is a flow chart of the communication optimization module of the present invention; Figure 4 It is a flow chart of the data acquisition module of the present invention; Figure 5 is a flow chart of the abnormality detection module of the present invention; Figure 6 This is a flow chart of the leakage monitoring module of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0018] Example 1: Please refer to Figure 1 , a fermentation tank backfill soil monitoring system based on a sensor network includes: The temperature and humidity prediction module obtains microbial metabolic characteristic data, calculates the metabolic heat release rate and water vapor release rate in multiple fermentation stages, analyzes the temperature and humidity change characteristics, and establishes a temperature and humidity benchmark prediction model; The communication optimization module calls the temperature and humidity benchmark prediction model to obtain the geographical location, wireless signal strength, and energy consumption level of the sensor nodes. By calculating the cost and signal quality of data transmission between nodes, it adjusts and optimizes the data flow path and generates an optimized communication path. The data acquisition module calls the optimized communication path and uses sensors to obtain the temperature and humidity data of the backfill soil and the concentration data of various gases in real time. By analyzing the rate of change of the data, the data acquisition frequency of the sensor is adjusted to obtain the acquisition frequency parameters; The anomaly detection module uses the acquisition frequency parameters to calculate the temperature gradient change rate and gas concentration change trend of multiple areas in real time, and analyzes and detects the abnormal heat diffusion path in combination with the backfill soil moisture status to generate the heat transfer anomaly judgment value; The leakage monitoring module calls the heat transfer anomaly judgment value, detects gas leakage in real time and generates leakage monitoring results based on the real-time change rate of carbon dioxide and oxygen concentrations, combined with the porosity and real-time humidity status of the backfill soil, by identifying and analyzing the diffusion path of the gas.

[0019] The temperature and humidity benchmark prediction model specifically includes the metabolic heat release rate, water vapor release rate, and temperature and humidity change trend. The optimized communication path includes the data transmission cost between nodes, signal quality, and data flow path. The acquisition frequency parameters specifically include the temperature and humidity data change rate, the change rate of multiple gas concentrations, and the sensor acquisition frequency adjustment value. The heat transfer anomaly judgment value includes the temperature gradient change rate, gas concentration change trend, and abnormal heat diffusion path. The leakage monitoring results specifically refer to the carbon dioxide concentration change rate, oxygen concentration change rate, and gas diffusion path.

[0020] See also Figure 2 , the temperature and humidity prediction module includes: The metabolic heat calculation submodule obtains microbial metabolic characteristic data, including oxygen consumption rate and carbon dioxide release rate. According to the heat changes of oxygen consumption and carbon dioxide release, the formula is used: ; Calculate the metabolic heat release rate per unit volume to obtain the heat release rate; in, represents the metabolic heat release rate, represents the calorific value of oxygen combustion, Representative The oxygen consumption rate at a given moment is represents the calorific value of carbon dioxide combustion, Representative The carbon dioxide release rate at a given moment is represents the unit volume, represents the total number of time steps, represents the index of the time step; In the process of calculating the metabolic heat release rate, it is first necessary to obtain the microbial metabolic characteristic data, including the oxygen consumption rate and the carbon dioxide release rate The acquisition of these data usually relies on a real-time online gas analyzer, which measures the oxygen and carbon dioxide concentrations of the fermentation tank exhaust and calculates the hourly gas exchange rate in combination with the gas flow rate. In order to ensure the accuracy of the measurement data, the equipment must be calibrated before measurement, and the measurement data must be drift corrected to eliminate the impact of ambient temperature and pressure changes on the measurement value, and then the metabolic heat release rate per unit volume is calculated. The calorific value of oxygen combustion should be considered and CO2 combustion calorific value , calculate the heat release caused by oxygen consumption and heat loss due to carbon dioxide generation , for all time steps Sum and divide by the unit volume To obtain the metabolic heat release rate , thus obtaining the heat release rate in different time periods.

[0021] The metabolic heat release rate was calculated using the formula: ; in, represents the metabolic heat release rate ( ), represents the heat of combustion of oxygen (kJ / mol), Representative Oxygen consumption rate at time (mmol / L·h), represents the heat of combustion of carbon dioxide (kJ / mol), Representative Carbon dioxide release rate at time (mmol / L·h), Represents unit volume ( ), represents the total number of time steps, An index representing a time.

[0022] set up kJ / mol, kJ / mol, per unit volume , time point The oxygen consumption rate mmol / L·h, carbon dioxide release rate mmol / L·h, then calculate : ; The results showed that at the time point When the metabolic heat release rate per unit volume is 50 , indicating that the oxygen consumption of microorganisms at this stage is relatively active, and the heat released during metabolism is relatively high. Continued increase may mean that microbial metabolic activity is accelerating. A decrease in the level of creatinine may indicate a metabolic slowdown or a decrease in nutrients in the culture medium.

[0023] The water vapor release calculation submodule calls the heat release rate and uses the oxygen consumption rate and carbon dioxide release rate to calculate the water vapor release rate; In the process of calculating the water vapor release rate, the metabolic heat release rate must first be called , combined with the oxygen consumption rate and the carbon dioxide release rate To estimate the water vapor release rate The calculation of water vapor release rate depends on the water vapor generation coefficient , which can be obtained by fitting the experimental data of water loss during fermentation. The generation of water vapor mainly comes from the respiration of microorganisms and the evaporation of water in the fermentation products. The temperature and air flow rate in the fermentation tank will also affect the amount of water vapor released. Therefore, when calculating the water vapor release rate, it is necessary to comprehensively consider the oxygen consumption and carbon dioxide generation, and combine the experimentally measured The value is calculated for correction.

[0024] The water vapor release rate was calculated using the formula: ; in, is the water vapor release rate (g / L·h), is the water vapor generation coefficient, For the Oxygen consumption rate at time (mmol / L·h), For the Carbon dioxide release rate at time (mmol / L·h), is the total number of time steps.

[0025] set up , time point The oxygen consumption rate mmol / L·h, carbon dioxide release rate mmol / L·h, then calculate the water vapor release rate : ; The results showed that the water vapor release rate per unit volume was 1.5 g / L·h. If this value continued to increase, it would indicate that the water vapor concentration in the fermenter was rising, and the ventilation rate or temperature control strategy might need to be adjusted to prevent excessive water loss from affecting the culture medium concentration.

[0026] The temperature and humidity prediction modeling submodule calls the water vapor release rate, combines the heat release rate data of each fermentation stage, records the temperature and humidity change characteristics of multiple fermentation stages, and constructs a temperature and humidity benchmark prediction model; When calculating the temperature and humidity trend changes, you need to first call the water vapor release rate , combined with the heat release rate of each fermentation stage The temperature change rate is calculated using As a driving factor, combined with the temperature variation coefficient Calculate the change of temperature over time, and the change of humidity is calculated by Combined humidity coefficient of variation Calculate humidity values ​​and temperature variation coefficients at different time points reflects the effect of heat release on ambient temperature, while the humidity variation coefficient It represents the contribution of water vapor release rate to humidity change. Both can be obtained through experimental measurement and adjusted according to the temperature and humidity control strategy of the fermentation environment.

[0027] The temperature and humidity change trend is calculated using the formula: ; in, For the The temperature of the moment, is the temperature at the previous moment, is the temperature variation coefficient, is the metabolic heat release rate, For the Humidity at all times, is the humidity at the previous moment, is the humidity variation coefficient, is the water vapor release rate.

[0028] set up , , initial temperature , initial humidity , time point Time calculation and : ; ; After calculation, it was found that The temperature reached 38.5℃ and the humidity rose to 80.5%.

[0029] At the point in time Calculated and , indicating that under the action of metabolic heat release and water vapor release, the temperature and humidity have increased. If they continue to rise at subsequent time points, the cooling system or dehumidification system may need to be adjusted to maintain a suitable fermentation environment. If the temperature and humidity are too high, the growth of microorganisms may be inhibited. If they are too low, the metabolic activity may be affected.

[0030] See also Figure 3 , the communication optimization module includes: The data acquisition submodule calls the temperature and humidity benchmark prediction model to obtain the geographical location, wireless signal strength, and energy consumption level of the sensor node, and generates a node information data set; In the application of sensor networks, first of all, it is necessary to obtain the geographic location, wireless signal strength and energy consumption level from the sensor node. These data can help determine the basic environmental conditions of each node as the basis for subsequent calculations. In order to ensure the accuracy and real-time nature of these data, the sensor node will regularly upload its location data, and obtain the precise location of the node through the GPS module or the positioning algorithm based on the known location. The location data is usually in longitude and latitude (for example: the location of node 1 is (30.2672°N, 97.7431°W)). The wireless signal strength is usually measured by the RSSI (received signal strength indication) value in dBm. Common values ​​may be 60dBm, 70dBm, etc., reflecting the communication quality between nodes. The energy consumption level is obtained by measuring the change of current and voltage by the sensor. After obtaining the node location, wireless signal strength and energy consumption data, they are input into the system for subsequent analysis and serve as the basis for transmission cost and signal quality analysis.

[0031] Assume that the geographical location of node 1 is (30.2672°N, 97.7431°W), the wireless signal strength is 65dBm, and the energy consumption level is 150mAh. We input these data into the system for subsequent calculations. Assume that the strength of the transmission signal is 65dBm, the distance is 100 meters, and the energy consumption is 150mAh. As a numerical example in practical applications, these data will affect the transmission path selection and energy optimization calculation.

[0032] The signal quality analysis submodule calls the node information data set, analyzes and records the transmission cost and signal quality between multiple nodes, and generates a signal quality evaluation value; Next, the feasibility of each communication path is evaluated by analyzing the transmission cost and signal quality between multiple nodes. The transmission cost is usually determined by factors such as the distance between nodes and the energy required. A common calculation method is to estimate the cost based on the distance between nodes and the battery consumption of the current node. For example, if the distance between two nodes is 100 meters, the battery power is 200mAh, and the energy consumption of transmitting data through a certain protocol is 50mAh, then the cost of this path can be expressed as 50mAh. Signal quality analysis is based on the wireless signal strength (RSSI value) to judge the reliability of the signal. A low RSSI value (for example: 90dBm) may mean poor signal quality, while a higher value (for example: 50dBm) indicates good signal quality. By calculating the mean and variance of the signal quality between nodes, the network stability and the reliability of data transmission can be determined. These data will become an important basis for optimizing communication paths.

[0033] The transmission cost is calculated by the following formula: ; in, is the transmission cost of the path, is the distance between nodes (unit: meter), The energy required for a single transmission (unit: mAh), is the total energy of the node (unit: mAh).

[0034] Assume that the distance between nodes Meter, transmitted energy mAh, total node energy mAh, the transmission cost is: ; This means the transmission cost for this path is 25mAh.

[0035] The path score calculation submodule uses the formula based on the signal quality evaluation value: ; Calculate the scores of multiple signal transmission paths, adjust and optimize the data flow path by comparing the scores of multiple paths, and generate an optimized communication path; in, represents the path score, represents the signal quality between the bth pair of nodes in the path, represents the transmission cost between the bth pair of nodes in the path, A weighting factor representing the signal quality, The weight factor representing the cost, represents the total number of node pairs in the path, Represents the index of the node pair in the path; Finally, by calculating the scores of multiple paths, the data flow path is adjusted and optimized. The path score is usually completed by weighted summing the transmission cost and signal quality between each pair of nodes in each path. Specifically, the path score is calculated as follows: ; in, is the path score, is the signal quality between the b-th pair of nodes, is the transmission cost between the bth pair of nodes, and are the weights of signal quality and cost respectively. The weight setting is usually adjusted according to actual needs. For example, when signal quality is more important, can be set to a larger value (e.g. 0.7), while the weight of the transmission cost ( ) can be set to a small value (for example, 0.3). These weights reflect the relative importance of signal quality and cost to path selection.

[0036] Assume that there are 3 paths, each path contains 3 node pairs, and the signal quality and transmission cost are: Path 1, dBm, mAh, Path 2, dBm, mAh, Path 3, dBm, mAh; The weights are set to, , ; According to the formula, the path score is calculated as follows: ; ; ; Finally, path 1 has the highest score, so path 1 is selected as the optimization path.

[0037] See also Figure 4 , the data acquisition module includes: The sensor data acquisition submodule calls the optimized communication path to obtain the temperature and humidity data and the concentration data of various gases of each sensor node and generate the original acquisition data; During the data collection process, the role of the sensor node is to periodically collect and transmit environmental data, usually including temperature, humidity, and gas concentration. The data is collected by the set sensor device at a predetermined time interval. Each sensor node monitors environmental changes in its working area and sends the collected data regularly. The sensor device generally transmits the collected environmental data to the central processing system in real time through wireless communication protocols (such as WiFi, LoRa, Zigbee, etc.). Through the data collection function, the sensor can monitor multiple physical quantities at the same time and adjust the data collection strategy according to different collection conditions (such as time intervals, environmental changes, etc.). For example, the temperature sensor records the current temperature value each time it collects, the humidity sensor records the air humidity value, and the gas sensor can detect and record the concentration of gases such as carbon dioxide and nitrogen dioxide. For each data point, the sensor will measure and record the value regularly. For example, suppose that at a certain moment, the temperature value recorded by the sensor is 25℃, the humidity is 60%, and the carbon dioxide concentration is 400ppm. These data are transmitted to the central system in real time and processed later through the data communication module. These raw data provide the basis for subsequent analysis and optimization. During the transmission process, data stability and accuracy are ensured through data caching and redundancy verification. These data collection operations are carried out continuously to ensure that environmental changes in the monitoring area can be fed back and processed in real time.

[0038] The change rate analysis submodule calls the original collected data, analyzes the data change rate based on the temperature and humidity data and gas concentration data collected by the sensor, evaluates the change trend, and generates the data change rate; As data collection proceeds, the next step is to analyze the rate of change of the collected data. The calculation of the rate of change is usually used to quantify the speed of change of environmental parameters so that the collection frequency can be adjusted and resource usage can be optimized based on the rate of change. The specific rate of change analysis process includes two aspects: first, obtain the data at consecutive time points, then calculate the change between these data, and then combine the change with the time interval to obtain the rate of change. This process is performed independently for each type of data (temperature, humidity, and gas concentration). For example, if the temperature changes by 5°C between two time points and the time interval is 2 hours, the temperature change rate is: ; in, and Respectively represent the current value of temperature and the value of the previous moment, is the time interval. Assuming the temperature change is 5°C and the time interval is 2 hours, the temperature change rate is: ; By obtaining the change rates of temperature, humidity and gas concentration, the system will be able to identify the speed of environmental changes and determine whether it is necessary to increase the frequency of data collection to cope with environmental fluctuations, ensuring data accuracy and timely response.

[0039] The acquisition frequency adjustment submodule is based on the data change rate and uses the formula: ; Calculate the acquisition frequency adjustment value, adjust the data acquisition frequency, and obtain the acquisition frequency parameters; in, represents the adjusted acquisition frequency, Represents the amount of data change, represents the time variation, represents the temperature change weight, represents the humidity change weight, Represents the weight of gas concentration change; Finally, based on the calculated change rate results, the system will adjust the frequency of data collection. The adjustment of the collection frequency is dynamically optimized according to the speed of data change: when the environment changes rapidly, the collection frequency needs to be increased to ensure that all changes are captured quickly; when the environment changes relatively smoothly, the collection frequency can be reduced to save computing resources and battery energy. Specifically, the adjustment of the collection frequency depends on the calculation results of the change rate. When the temperature change rate is higher than a preset threshold (such as 5℃ / h), the system will adjust the collection frequency to once per minute; if the change rate is lower (such as lower than 0.5℃ / h), the system will adjust it to once every 10 minutes. To achieve this adjustment, the system uses the following formula to calculate the collection frequency: ; in, represents the adjusted acquisition frequency, Represents the amount of data change, represents the time variation, is the temperature change weight, is the humidity change weight, is the gas concentration change weight.

[0040] For example, assume that the temperature change is 5°C, the time interval is 1 hour, the humidity change is 3%, the gas concentration change is 10ppm, and the corresponding weights are set as follows: (temperature change weight), (humidity change weight), (Gas concentration change weight).

[0041] According to the formula, the calculation result of the acquisition frequency is: ; This result shows that under the current conditions of changing temperature, humidity and gas concentration, the system needs to adjust the collection frequency to 10 times per second to ensure the real-time and accuracy of capturing data changes.

[0042] See also Figure 5 , the anomaly detection module includes: The temperature gradient calculation submodule uses the acquisition frequency parameters to obtain temperature data of multiple areas in real time, calculates the temperature difference between each area, and identifies the speed and direction of heat diffusion in combination with the position coordinates to obtain the temperature gradient change rate; To obtain temperature data of multiple areas, it is necessary to collect data from multiple sensor nodes. First, determine the coordinates of each measuring point and record their relative positions, such as , For a certain time interval Temperature changes within the room, data recorded by sensors, and time acquisition and Corresponding temperature value and , calculate the temperature difference between different measuring points in the area, the formula is as follows: ; Then the temperature gradient change rate is calculated based on the spatial distance of the measuring points. ,Right now ; in, is the distance between the measuring points. The distance between the measuring points can be calculated using the spatial Euclidean distance, that is, ; Assume that a sensor A is Location, temperature , sensor B is Location, temperature ,but: ; ; ; This calculation shows that the rate of change of the temperature gradient is , which can be used for subsequent gas concentration trend analysis.

[0043] The gas concentration trend analysis submodule uses gas concentration data to calculate the changing trends of multiple gas concentrations in each area in real time based on the temperature gradient changing rate, analyzes the gas diffusion rate, and obtains the gas concentration trend offset; After the temperature gradient change rate is calculated, the gas concentration data is used for real-time calculation, the gas concentration data of multiple measuring points are compared, and the concentration changes between adjacent measuring points are calculated. , the formula is as follows: ; in, is the gas concentration trend offset (unit: %), is the difference in gas concentration between adjacent measuring points (unit: ppm), is the distance between measuring points (unit: m).

[0044] Assume that the carbon dioxide concentration at a certain measuring point A is 400ppm, the concentration at measuring point B is 420ppm, and the distance between measuring points A and B is 3m, then ; ; Calculated The value indicates that the gas concentration changes by 6.67% within a distance of 3 m, which can be used to further analyze the gas diffusion rate.

[0045] Table 1: Measurement point temperature and humidity data and calculation results

[0046] As shown in Table 1, the temperature gradient and gas concentration trend offsets have been calculated and can be used for further heat transfer anomaly analysis.

[0047] The heat transfer anomaly determination submodule is based on the gas concentration trend offset and the measured value of backfill soil humidity, using the formula: ; Calculate the heat diffusion path anomaly coefficient and generate the heat transfer anomaly judgment value; in, represents the heat diffusion path anomaly coefficient, Represents the gas concentration trend offset, represents the rate of change of temperature gradient, Represents the measured value of backfill soil moisture, represents the data collection time interval, Represents the absolute value of humidity change rate; Based on gas concentration trend offset And the measured value of backfill soil moisture , calculate the heat diffusion path anomaly coefficient , using the formula: ; in, represents the heat diffusion path anomaly coefficient, is the gas concentration trend offset, is the temperature gradient change rate, is the measured value of backfill soil moisture, is the data collection time interval, is the absolute value of the humidity change rate. Assume that the parameter values ​​are as follows: , , , , , bring into calculation: ; ; ; ; Calculated heat diffusion path anomaly coefficient , indicating that there is a certain degree of thermal diffusion anomaly in the area. This value can be compared with the preset threshold to determine whether to trigger an alarm or further optimize the data collection strategy.

[0048] See also Figure 6 , the leakage monitoring module includes: The gas diffusion resistance calculation submodule calls the heat transfer anomaly judgment value, combines the backfill soil porosity and real-time humidity status data, evaluates the degree of gas restriction, calculates the restriction of gas flow, evaluates the diffusion capacity of gas in multiple areas, and obtains gas diffusion resistance data; In the fermentation tank backfill soil monitoring system, the heat transfer anomaly judgment value is first obtained. This value monitors the temperature changes of each area of ​​the backfill soil in real time through the sensor and calculates the temperature gradient change rate. The temperature gradient can be calculated by the following formula: ; in, is the temperature gradient (℃ / cm), is the temperature of measuring point 2 (°C), is the temperature of measuring point 1 (℃), is the distance between measuring point 1 and measuring point 2 (cm).

[0049] Set the assumed value: , , , then the calculation is as follows: ; The calculated temperature gradient is 0.5°C / cm, which is a high value, indicating that there is a large heat transfer anomaly in this area.

[0050] Next, obtain the porosity data of the backfill soil. Porosity represents the ratio of the pore volume in the soil to the total soil volume and can be calculated using the following formula: ; in, is the soil porosity (%), is the pore volume (cm3), is the total volume of soil (cubic centimeters).

[0051] Set the assumed value: Cubic centimeters, Cubic centimeters, then the calculation is as follows: ; The calculated porosity is 40%, indicating that the soil in this area contains a high proportion of pores, which may have an impact on gas diffusion.

[0052] Subsequently, real-time humidity status data is obtained. Humidity affects the diffusion capacity of gas in the soil, which can be measured in real time by humidity sensors. For example, the humidity sensor in a certain area shows that the humidity is 20%. Then, the degree of gas restriction is evaluated, and the relationship between the temperature abnormality area and the porosity and humidity is analyzed to determine the flow restriction of gas in these areas.

[0053] Next, calculate the restriction of gas flow using the gas diffusion resistance calculation formula: ; in, is the gas diffusion resistance (s / cm²), is the thickness of the soil layer through which the gas passes (cm), is the gas diffusion coefficient (cm² / s).

[0054] Set the assumed value: cm, cm² / s, then the calculation is as follows: ; The calculated gas diffusion resistance is 1500s / cm², which is a large value, indicating that gas diffusion in this area is difficult.

[0055] The gas flow direction determination submodule calls the gas diffusion resistance data, combines the gas concentration change trend data, calculates the diffusion gradient between multiple measuring points, compares the diffusion resistance of each area, analyzes the gas flow direction, and obtains the gas flow direction information; In the fermentation tank backfill soil monitoring system, the gas diffusion resistance data is first called to indicate the resistance of the soil in each area to gas diffusion. Then, the gas concentration change trend data is obtained, and the gas concentration in each area is monitored in real time through sensors, and its change over time is recorded. Then, the diffusion gradient between multiple measuring points is calculated using the following formula: ; in, is the gas diffusion gradient (% / cm), is the gas concentration at measuring point 2 (%), is the gas concentration at measuring point 1 (%), is the distance between measuring point 1 and measuring point 2 (cm).

[0056] Set the assumed value: , , cm, the calculation is as follows: ; The calculated gas diffusion gradient is 0.004% / cm, indicating that the gas concentration in this area varies greatly.

[0057] Finally, the gas flow direction is analyzed and the gas flow direction information is determined by combining the concentration gradient and diffusion resistance data.

[0058] The leakage risk assessment submodule calls the gas flow direction information and combines it with the gas diffusion resistance data to identify the distribution of gas in multiple areas using the formula: ; Calculate the leakage risk index of each area, detect gas leakage, and generate leakage monitoring results; in, For the The leakage risk index of each region, For the In the region The target gas concentration at each measuring point is For the In the region The gas diffusion gradient at each measuring point is For the In the region The gas diffusion resistance at each measuring point is For the In the region Environmental impact factors of each measuring point, For Region The total number of measuring points within In the fermentation tank backfill soil monitoring system, the gas flow direction information is first called, which is obtained through the above steps and represents the flow trend of gas in different areas. Then, combined with the gas diffusion resistance data, the distribution of gas in multiple areas is identified.

[0059] Next, the leakage risk index for each area is calculated using the following formula: ; in, For the The leakage risk index of each region, For the In the region Target gas concentration at each measuring point (%), For the In the region Gas diffusion gradient at each measuring point (% / cm), For the In the region Gas diffusion resistance at each measuring point (s / cm²), For the In the region Environmental impact factors of each measuring point, For Region The total number of measurement points within .

[0060] Set the assumed value: , , ; , , ; , , ; , , .

[0061] Enter the formula to calculate: ; The calculation results are used to assess the leakage risk level in the area.

[0062] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A fermentation tank backfill soil monitoring system based on a sensor network, characterized in that: The system comprises: The temperature and humidity prediction module obtains microbial metabolic characteristic data, calculates the metabolic heat release rate and water vapor release rate in multiple fermentation stages, analyzes the temperature and humidity change characteristics, and establishes a temperature and humidity benchmark prediction model; The communication optimization module calls the temperature and humidity benchmark prediction model to obtain the geographical location, wireless signal strength, and energy consumption level of the sensor node, and adjusts and optimizes the data flow path by calculating the cost and signal quality of data transmission between nodes to generate an optimized communication path; The data acquisition module calls the optimized communication path and uses sensors to obtain the temperature and humidity data of the backfill soil and the concentration data of various gases in real time, and adjusts the data acquisition frequency of the sensor by analyzing the rate of change of the data to obtain the acquisition frequency parameters; The anomaly detection module uses the acquisition frequency parameters to calculate the temperature gradient change rate and gas concentration change trend of multiple regions in real time, combines the backfill soil moisture status, analyzes and detects abnormal heat diffusion paths, and generates heat transfer anomaly judgment values.

2. The fermentation tank backfill soil monitoring system based on sensor network according to claim 1 is characterized in that: The temperature and humidity benchmark prediction model specifically includes metabolic heat release rate, water vapor release rate, and temperature and humidity change trend; the optimized communication path includes data transmission cost, signal quality, and data flow path between nodes; the acquisition frequency parameters specifically include temperature and humidity data change rate, multiple gas concentration change rate, and sensor acquisition frequency adjustment value; the heat transfer anomaly judgment value includes temperature gradient change rate, gas concentration change trend, and abnormal heat diffusion path.

3. The fermentation tank backfill soil monitoring system based on sensor network according to claim 1 is characterized in that: The temperature and humidity prediction module includes: The metabolic heat calculation submodule obtains microbial metabolic characteristic data, including oxygen consumption rate and carbon dioxide release rate. According to the heat changes of oxygen consumption and carbon dioxide release, the formula is used: ； Calculate the metabolic heat release rate per unit volume to obtain the heat release rate; in, represents the metabolic heat release rate, represents the calorific value of oxygen combustion, Representative The oxygen consumption rate at a given moment is represents the calorific value of carbon dioxide combustion, Representative The carbon dioxide release rate at a given moment is represents the unit volume, represents the total number of time steps, represents the index of the time step; The water vapor release calculation submodule calls the heat release rate and calculates the water vapor release rate using the oxygen consumption rate and the carbon dioxide release rate; The temperature and humidity prediction modeling submodule calls the water vapor release rate, combines the heat release rate data of each fermentation stage, records the temperature and humidity change characteristics of multiple fermentation stages, and constructs a temperature and humidity benchmark prediction model.

4. The fermentation tank backfill soil monitoring system based on sensor network according to claim 1 is characterized in that: The communication optimization module includes: The data acquisition submodule calls the temperature and humidity benchmark prediction model to obtain the geographical location, wireless signal strength, and energy consumption level of the sensor node, and generates a node information data set; The signal quality analysis submodule calls the node information data set, analyzes and records the transmission cost and signal quality between multiple nodes, and generates a signal quality evaluation value; The path score calculation submodule uses the formula: ； Calculate the scores of multiple signal transmission paths, adjust and optimize the data flow path by comparing the scores of multiple paths, and generate an optimized communication path; in, represents the path score, represents the signal quality between the bth pair of nodes in the path, represents the transmission cost between the bth pair of nodes in the path, A weighting factor representing the signal quality, The weight factor representing the cost, represents the total number of node pairs in the path, Represents the index of a node pair in a path.

5. The fermentation tank backfill soil monitoring system based on sensor network according to claim 1 is characterized in that: The data acquisition module comprises: The sensor data acquisition submodule calls the optimized communication path to obtain the temperature and humidity data and the concentration data of multiple gases of each sensor node, and generates raw acquisition data; The change rate analysis submodule calls the original collected data, analyzes the change rate of the data according to the temperature and humidity data and gas concentration data collected by the sensor, evaluates the change trend, and generates the data change rate; The acquisition frequency adjustment submodule adopts the formula based on the data change rate: ； Calculate the acquisition frequency adjustment value, adjust the data acquisition frequency, and obtain the acquisition frequency parameters; in, represents the adjusted acquisition frequency, Represents the amount of data change, represents the time variation, represents the temperature change weight, represents the humidity change weight, Represents the weight of gas concentration change.

6. The fermentation tank backfill soil monitoring system based on sensor network according to claim 1 is characterized in that: The anomaly detection module comprises: The temperature gradient calculation submodule uses the acquisition frequency parameters to obtain temperature data of multiple regions in real time, calculates the temperature difference between each region, identifies the speed and direction of heat diffusion in combination with the position coordinates, and obtains the temperature gradient change rate; The gas concentration trend analysis submodule calculates the change trend of multiple gas concentrations in each area in real time based on the temperature gradient change rate and the gas concentration data, analyzes the gas diffusion rate, and obtains the gas concentration trend offset; The heat transfer anomaly determination submodule adopts the formula based on the gas concentration trend offset and the measured value of backfill soil humidity: ； Calculate the heat diffusion path anomaly coefficient and generate the heat transfer anomaly judgment value; in, represents the heat diffusion path anomaly coefficient, Represents the gas concentration trend offset, represents the rate of change of temperature gradient, Represents the measured value of backfill soil moisture, represents the data collection time interval, Represents the absolute value of the humidity change rate.

7. The fermentation tank backfill soil monitoring system based on sensor network according to claim 1 is characterized in that: The system further comprises: The leakage monitoring module calls the heat transfer anomaly judgment value, detects gas leakage in real time and generates leakage monitoring results by identifying and analyzing the diffusion path of the gas according to the real-time change rate of carbon dioxide and oxygen concentrations, combined with the porosity and real-time humidity state of the backfill soil; The leakage monitoring results specifically refer to the rate of change of carbon dioxide concentration, the rate of change of oxygen concentration, and the gas diffusion path.

8. The fermentation tank backfill soil monitoring system based on sensor network according to claim 7 is characterized in that: The leakage monitoring module comprises: The gas diffusion resistance calculation submodule calls the heat transfer anomaly judgment value, combines the backfill soil porosity and real-time humidity status data, evaluates the degree of gas restriction, calculates the restriction of gas flow, evaluates the diffusion capacity of gas in multiple areas, and obtains gas diffusion resistance data; The gas flow direction determination submodule calls the gas diffusion resistance data, combines the gas concentration change trend data, calculates the diffusion gradient between multiple measuring points, compares the diffusion resistance of each area, analyzes the gas flow direction, and obtains the gas flow direction information; The leakage risk assessment submodule calls the gas flow direction information, combines the gas diffusion resistance data, identifies the distribution of gas in multiple areas, and uses the formula: ； Calculate the leakage risk index of each area, detect gas leakage, and generate leakage monitoring results; in, For the The leakage risk index of each region, For the In the region The target gas concentration at each measuring point is For the In the region The gas diffusion gradient at each measuring point is For the In the region The gas diffusion resistance at each measuring point is For the In the region Environmental impact factors of each measuring point, For Region The total number of measurement points within.

Images