Optimization method and system based on gas concentration regulation and control, terminal and medium

Abstract

The invention relates to an optimization method and system based on gas concentration regulation and control, a terminal and a medium, and relates to the field of environmental monitoring, and the method comprises the steps: collecting gas concentration data in real time through a gas detection device in a farm; when the gas concentration data exceeds a safety threshold value, obtaining a predicted laying rate according to a prediction result output by the gas concentration-laying rate correlation model; starting a hierarchical regulation mechanism according to the predicted laying rate; after the hierarchical regulation and control mechanism is started, judging whether the gas concentration data meets a preset requirement or not; if not, the sampling frequency and the detection precision of the gas detection device are improved under the condition that it is detected that the gas concentration data exceed the safety threshold value or the decline rate of the gas concentration data is lower than the rate threshold value; the spatial distribution density of the gas detection device is improved; adjusting an equipment state corresponding to the hierarchical regulation and control mechanism; otherwise, closing the hierarchical regulation and control mechanism. The method has the effects of promoting efficient production of livestock and poultry and improving breeding benefits.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of environmental monitoring, and in particular to an optimization method, system, terminal and medium based on gas concentration regulation. BACKGROUND

[0002] In modern livestock and poultry breeding management, gas concentration regulation is a key technical support for promoting efficient production of livestock and poultry and improving breeding efficiency.

[0003] In related technologies, the breeding farm environmental monitoring system is based on single gas sensor technology, which periodically collects environmental gas concentration data, compares it with the preset safety threshold, triggers the start-stop control of the ventilation equipment, and finally maintains the basic environmental conditions in the breeding house.

[0004] For the related technologies in the above, in the gas concentration regulation, there are problems of insufficient reliability of monitoring data and rigid regulation strategy, which leads to large fluctuations in environmental parameters and lag in emergency response, seriously affecting the stability of livestock and poultry production and breeding efficiency. SUMMARY

[0005] In order to promote efficient production of livestock and poultry and improve breeding efficiency, the present application provides an optimization method, system, terminal and medium based on gas concentration regulation.

[0006] In a first aspect, the present application provides an optimization method based on gas concentration regulation, which adopts the following technical solution: An optimization method based on gas concentration regulation, comprising collecting gas concentration data in real time through a gas detection device in a breeding farm, wherein the gas concentration data includes ammonia, hydrogen sulfide and carbon dioxide; When the gas concentration data exceeds the safety threshold, a predicted egg production rate is obtained according to the prediction result output by the gas concentration-egg production rate correlation model; Starting a hierarchical regulation mechanism according to the predicted egg production rate; After starting the hierarchical regulation mechanism, it is judged whether the gas concentration data meets the preset requirements; If not, in the case of detecting that the gas concentration data exceeds the safety threshold, or the decline rate of the gas concentration data is lower than the rate threshold, the sampling frequency and detection accuracy of the gas detection device are improved; the spatial distribution density of the gas detection device is improved; the device state corresponding to the hierarchical regulation mechanism is adjusted; In the case of detecting that the gas concentration data does not exceed the safety threshold, and the decline rate of the gas concentration data is not lower than the rate threshold, the hierarchical regulation mechanism is closed.

[0007] By adopting the above technical solution, the concentrations of ammonia, hydrogen sulfide, and carbon dioxide in the farm are monitored in real time. Combined with an egg production performance prediction model, the degree of environmental hazard is intelligently analyzed. Simultaneously, the optimal response plan is automatically matched from the equipment control strategy library, precisely triggering a tiered control mechanism. This solution significantly improves the timeliness and accuracy of environmental control, maximizing the economic benefits of poultry farming while ensuring poultry welfare.

[0008] Optionally, a device power consumption database is established, which is used to store power consumption data of ventilation systems, spray deodorization devices, and feed feeding systems; When the gas concentration data is detected to synchronously exceed the safety threshold, the predicted egg production rate loss value corresponding to each gas exceeding the standard is calculated according to the gas concentration-egg production rate correlation model. The predicted egg production rate loss values ​​are sorted in descending order to generate an execution queue for priority control instructions. The remaining load capacity of the distribution box is dynamically calculated by calling the device power consumption data in the device power consumption database. Based on the remaining load capacity of the distribution box, the control equipment is activated in the order of the execution queue to satisfy: P1+P2+...+P k ≤P remain P k P represents the real-time power consumption of the k-th device to be started. remain This represents the current remaining available load capacity. A delay compensation mechanism is initiated for the execution queue that has not yet been executed.

[0009] By adopting the above technical solution, combined with an egg production performance prediction model to intelligently assess the level of environmental hazards, and simultaneously accurately matching the optimal control scheme from the equipment control strategy library, the solution automatically triggers tiered control commands. This solution significantly improves the accuracy of environmental control, optimizes equipment resource scheduling, avoids over- or under-control, and significantly improves poultry house environmental quality and breeding production efficiency.

[0010] Optionally, the device power consumption database is queried to identify devices in the execution queue whose startup transient current exceeds N times the rated operating current, and the rated power of the devices to be started is extracted. Calculate the minimum start-up time interval based on the rated power; The minimum capacity requirement of the buffer capacitor bank is determined based on the minimum start-up time interval and the device current parameters, wherein the device current parameters include the start-up transient current and the rated operating current. Based on the minimum capacity requirement, the current fluctuation amplitude is detected in real time during equipment startup; When the current fluctuation exceeds the allowable upper limit, the minimum capacity requirement of subsequent devices is automatically increased and the device power consumption database is updated.

[0011] By adopting the above technical solutions, dynamically optimizing equipment startup timing and intelligently configuring power buffer capacitor banks, combined with a real-time power monitoring and feedback mechanism, stable power supply is achieved under the coordinated operation of multiple devices. This solution effectively solves the risks of instantaneous impacts and overloads faced by traditional farm power systems, significantly improving power supply reliability and equipment lifespan while ensuring timely response to environmental control measures.

[0012] Optionally, when the gas concentration data exceeds a safety threshold, increasing the sampling frequency and detection accuracy of the gas detection device further includes: Calculate the difference in CO2 concentration between the electrochemical sensor and the infrared sensor in the gas detection device; Determine whether the difference is greater than a difference threshold and whether the duration exceeds a time threshold; If so, it is determined that the infrared sensor is contaminated by particulate matter in the poultry house, triggering the optical path self-cleaning program. The particulate matter in the poultry house includes dust, feather debris, or water mist. The detection data of the electrochemical sensor is used as the master control data, and a confidence level label is added to the data detected by the infrared sensor. If not, remove the confidence level marker and restore the data fusion output of the electrochemical sensor and the infrared sensor.

[0013] By adopting the above technical solution, a dynamic reliability assessment mechanism is established by comparing the detection differences between the electrochemical sensor and the infrared sensor in real time, and a self-cleaning function for the optical path is added, enabling reliable monitoring in polluted environments in livestock farms. This solution ensures the continuity of monitoring data and significantly improves the system's anti-interference capability.

[0014] Optionally, the gas concentration data of the electrochemical sensor in the most recent time period can be obtained; If the gas concentration data continues to deviate from the reference value, and the gas concentration data exceeds a preset deviation threshold, and the duration of the gas concentration data exceeding the preset deviation threshold is greater than a preset duration, then the electrochemical sensor is determined to be invalid. The average concentration value is calculated based on the gas concentration data acquired by the infrared sensor within the most recent time period and used as temporary reference data. Activate the backup sensor and cross-validate the real-time data detected by the backup sensor with the temporary reference data; If the difference in the cross-validation is less than the cross-validation threshold, a validation pass signal is generated; In response to the verification pass signal, the status of the detection point corresponding to the backup sensor is marked as emergency mode, and an early warning signal is triggered, the early warning signal including a location code and a confidence index; Based on the warning signal, information on recommended maintenance measures is generated.

[0015] By adopting the above technical solutions, an electrochemical sensor effectiveness determination mechanism, an infrared sensor sliding window benchmark algorithm, and a backup sensor cross-validation process were established, constructing a complete self-diagnosis system for environmental monitoring faults. This solution achieves reliable transmission and intelligent verification of monitoring data, significantly improving the stability and data accuracy of the livestock farm gas monitoring system.

[0016] Optionally, the gas concentration data at multiple detection points in the farm can be collected in real time, and the gas concentration data includes the concentration value and the rate of change. By comparing and analyzing the gas concentration data with historical gas concentration data, the gas concentration change trend of the multiple detection points in the next monitoring cycle is predicted, and the prediction result is obtained. Based on the amount by which the prediction result exceeds the risk threshold, a risk level is set for the monitoring area corresponding to the detection point, and the risk level includes high risk, medium risk and low risk. Based on the prediction results and the risk level, a warning signal is sent.

[0017] By adopting the above-mentioned technical solution, combining real-time monitoring with historical data analysis, a dynamic risk assessment is established, enabling accurate prediction and tiered early warning of environmental risks. This solution can identify potential risk areas in advance and achieve differentiated early warning through a three-tiered risk classification, significantly improving the initiative and accuracy of environmental risk prevention and control in livestock farms.

[0018] Optionally, based on the real-time detected gas concentration data, when the growth rate of the target detection point in a single sampling cycle exceeds the average growth rate of adjacent points, a freeze command is generated. The freeze command includes the target detection point identifier, the abnormal increase value, and the average baseline value of adjacent points. Based on the freeze command, the historical data fluctuation range of the target detection point is retrieved and compared with the gas concentration data; If the gas concentration data continues to exceed the upper limit of the historical data fluctuation range, a device fault signal will be output. In response to the equipment fault signal, a data disable command is sent to the administrator terminal, and a forced calibration command is issued to the target detection point. The forced calibration command includes purge pressure and standard gas concentration. Acquire standard data, which is calibrated gas concentration data; When the number of samplings of the standard data reaches the standard threshold and the standard data returns to the historical data fluctuation range, a data recovery command is sent to the administrator terminal.

[0019] By adopting the above technical solutions, including real-time data anomaly detection, historical data comparison and analysis, and mandatory calibration processes, a complete equipment status monitoring system has been constructed. This solution significantly improves the reliability and data accuracy of the monitoring system, providing continuous and stable data support for farm environmental management and effectively avoiding the environmental control failures caused by equipment malfunctions in traditional monitoring systems.

[0020] Secondly, this application provides an optimization system based on gas concentration regulation, employing the following technical solution: An optimization system based on gas concentration regulation includes: The acquisition module is used to acquire gas concentration data and the gas concentration-egg production rate correlation model; A memory for storing the program of the optimized control method based on gas concentration regulation; The processor and the program in the memory can be loaded and executed by the processor to implement the optimized method based on gas concentration regulation.

[0021] By adopting the above technical solution, the monitoring module collects gas concentration data of the farm in real time, the processor dynamically executes the trend prediction algorithm, and the memory continuously optimizes the risk assessment model, realizing intelligent management of the entire process from environmental monitoring to graded early warning. While ensuring the accuracy of early warning, it significantly improves the efficiency of risk prevention and control, providing an intelligent and reliable solution for the environmental management of modern farms.

[0022] Thirdly, this application provides a smart terminal, which adopts the following technical solution: A smart terminal includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the method as described in any one of claims 1 to 7.

[0023] Fourthly, this application provides a computer storage medium capable of storing corresponding programs, which facilitates the promotion of efficient livestock and poultry production and improves breeding efficiency, and adopts the following technical solution: A computer-readable storage medium storing a computer program that can be loaded by a processor and executed any of the above-described optimization methods based on gas concentration regulation.

[0024] In summary, this application includes at least one of the following beneficial technical effects: 1. Real-time monitoring of ammonia, hydrogen sulfide, and carbon dioxide concentrations in poultry farms, combined with an egg production performance prediction model, intelligently analyzes the degree of environmental hazards and automatically matches the optimal response plan from the equipment control strategy library, precisely triggering a tiered control mechanism. This solution significantly improves the timeliness and accuracy of environmental control, maximizing the economic benefits of poultry farming while ensuring poultry welfare.

[0025] 2. An effectiveness determination mechanism for electrochemical sensors, a sliding window benchmark algorithm for infrared sensors, and a cross-validation process for backup sensors were established, constructing a complete self-diagnosis system for environmental monitoring faults. This scheme achieves reliable transmission and intelligent verification of monitoring data, significantly improving the stability and data accuracy of the gas monitoring system in livestock farms.

[0026] 3. A complete equipment status monitoring system is constructed through real-time data anomaly detection, historical data comparison and analysis, and mandatory calibration processes. This solution significantly improves the reliability and data accuracy of the monitoring system, providing continuous and stable data support for farm environmental management and effectively avoiding environmental control failures caused by equipment malfunctions in traditional monitoring systems. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating an optimization method based on gas concentration regulation provided in an embodiment of this application.

[0028] Figure 2 This is a flowchart illustrating an environmental control method based on egg production rate prediction provided in an embodiment of this application.

[0029] Figure 3 This is a schematic flowchart of a device startup control method based on power load optimization provided in an embodiment of this application.

[0030] Figure 4 This is a schematic flowchart of a gas monitoring method based on sensor difference detection provided in an embodiment of this application.

[0031] Figure 5 This is a schematic flowchart of a gas monitoring method based on sensor self-diagnosis provided in an embodiment of this application.

[0032] Figure 6 This is a flowchart illustrating a risk warning method based on predictive analysis provided in an embodiment of this application.

[0033] Figure 7 This is a schematic flowchart of a sensor intelligent calibration method based on anomaly detection provided in an embodiment of this application.

[0034] Figure 8 This is a schematic diagram of the structure of an optimization system based on gas concentration regulation provided in an embodiment of this application. Detailed Implementation

[0035] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1 to 8 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0036] This application discloses an optimization method based on gas concentration control. (Refer to...) Figure 1 The method includes: Step S101: Collect gas concentration data in real time using a gas detection device in the farm. The gas concentration data includes ammonia, hydrogen sulfide and carbon dioxide.

[0037] A gas detection device is a device used to detect the concentration of a specific gas in the environment in real time.

[0038] Gas concentration data refers to the concentration values ​​of various target gases obtained through gas detection devices.

[0039] For example, in a standard-sized chicken farm, a gas detection device is installed every 10 meters along the length of the chicken house, for a total of 6 devices. These devices automatically collect the concentration values ​​of NH3, H2S and CO2 every 5 minutes.

[0040] Step S102: When the gas concentration data exceeds the safety threshold, the predicted egg production rate is obtained based on the prediction results output by the gas concentration-egg production rate correlation model.

[0041] The gas concentration-egg production rate correlation model is a model built on gas concentration data and trained by machine learning algorithms. It is used to predict future egg production rate and confidence interval. The input parameters include the 24-hour dynamic change curve of each gas concentration, the exposure duration of gas combination, and the breed and age characteristics of the flock.

[0042] For example, by inputting the 24-hour dynamic change curves of NH3, H2S and CO2 over the past week, the combined exposure duration, and the age information of Hy-Line Brown chickens, the model predicts that the egg production rate of the farm will be 92% in the next 24 hours, with a confidence interval of ±3%.

[0043] Step S103: Activate the graded control mechanism based on the predicted egg production rate.

[0044] The graded control mechanism refers to the tiered activation of different environmental control measures based on the gas exceedance and its impact on egg production. The first-level control involves activating the ventilation system to prioritize reducing the NH3 concentration to less than or equal to 10 ppm. The second-level control involves triggering the spray deodorization device when the CO2 concentration is continuously higher than 3000 ppm. The third-level control involves linking the feed feeding system to add methionine preparations when the H2S concentration exceeds 5 ppm.

[0045] For example, when the predicted egg production rate decreases by 3.2% due to excessive NH3, the system will activate a tiered control mechanism, prioritizing the opening of the ventilation system to reduce ammonia concentration.

[0046] Step S104: After activating the graded control mechanism, determine whether the gas concentration data meets the preset requirements.

[0047] After the graded control mechanism is activated, the system continuously collects gas concentration data. If two consecutive detection results show that the gas concentration is lower than the safety threshold, it is determined that the preset requirements are met; otherwise, it is determined that the requirements are not met.

[0048] For example, the NH3 concentration is checked every 5 minutes. If two consecutive tests show that the NH3 concentration has dropped below 10 ppm, the gas concentration data is considered to meet the preset requirements; otherwise, the control strategy needs to be further adjusted.

[0049] Step S105: If not, if the gas concentration data exceeds the safety threshold or the rate of decrease of the gas concentration data is lower than the rate threshold, increase the sampling frequency and detection accuracy of the gas detection device.

[0050] Sampling frequency refers to the time interval at which a gas detection device acquires data.

[0051] For example, if the NH3 concentration is found to remain above 11 ppm or its rate of decrease is below the rate threshold during the control process, the system will automatically increase the sampling frequency of the gas detection device to once every 2 minutes and enhance the detection accuracy of the sensor.

[0052] Step S106: Increase the spatial distribution density of the gas detection device.

[0053] Spatial distribution density refers to the number of gas detection devices per unit area.

[0054] For example, if the NH3 concentration in a certain area remains at a high level for a long period of time, additional gas detection devices can be added to that area, such as increasing the number of devices from one per 10 meters to one per 5 meters.

[0055] Step S107: Adjust the equipment status corresponding to the hierarchical control mechanism.

[0056] Equipment status refers to the working mode or operating parameters of various types of equipment involved in regulation.

[0057] For example, when the system detects that the NH3 concentration is consistently higher than 10 ppm, in addition to increasing the power of the ventilation system, the direction of the ventilation openings can be adjusted or local enhanced ventilation equipment can be turned on to reduce the NH3 concentration more quickly.

[0058] Step S108: If the gas concentration data is detected to be within the safe threshold and the rate of decrease of the gas concentration data is not lower than the rate threshold, the graded control mechanism is turned off.

[0059] For example, if the NH3 concentration is detected to be stable below 8 ppm, the CO2 concentration drops to below 2800 ppm, and the H2S concentration remains below 2 ppm, and the rate of decrease of each gas concentration also meets the expected standard, then all graded control mechanisms are shut down and the normal operating mode is restored.

[0060] By adopting the above technical solution, the concentrations of ammonia, hydrogen sulfide, and carbon dioxide in the farm are monitored in real time. Combined with an egg production performance prediction model, the degree of environmental hazard is intelligently analyzed. Simultaneously, the optimal response plan is automatically matched from the equipment control strategy library, precisely triggering a tiered control mechanism. This solution significantly improves the timeliness and accuracy of environmental control, maximizing the economic benefits of poultry farming while ensuring poultry welfare.

[0061] This application discloses an environmental control method based on egg production rate prediction. (Refer to...) Figure 2 The method includes: Step S201: Establish a device power consumption database, which is used to store power consumption data of the ventilation system, spray deodorization device and feed feeding system.

[0062] The equipment power consumption database refers to a structured database used to store power consumption data of control equipment such as ventilation systems, spray deodorization devices, and feed feeding systems under different operating conditions.

[0063] For example, in a farm, an equipment power consumption database is established to record that the rated power of the ventilation system is 1.5kW and the average operating power consumption is 1.3kW; the power consumption of the spray deodorization device during a single spray cycle is 0.8kW; and the instantaneous power consumption of the feed feeding system during linkage operation is 0.5kW.

[0064] Step S202: When the gas concentration data is detected to exceed the safety threshold, calculate the predicted egg production rate loss value corresponding to each gas exceeding the standard according to the gas concentration-egg production rate correlation model.

[0065] The predicted loss in egg production rate refers to the decrease in future egg production rate relative to normal conditions, as predicted by a gas concentration-egg production rate correlation model.

[0066] The gas concentration-egg production rate correlation model outputs the predicted value of future egg production rate under the condition that each gas exceeds the standard individually. The difference between the benchmark egg production rate under normal conditions and the predicted value is used as the predicted egg production rate loss value for the corresponding gas.

[0067] For example, when the NH3 concentration is detected to be 14 ppm, the CO2 concentration to be 3200 ppm, and the H2S concentration to be 6 ppm, the gas concentration-egg production rate correlation model is invoked. Combined with the information that the flock is of the "Hy-Line Brown" breed and is 300 days old, it is calculated that NH3 exceeding the standard will lead to a 3.2% decrease in egg production rate, CO2 exceeding the standard will lead to a 1.8% decrease, and H2S exceeding the standard will lead to a 2.5% decrease.

[0068] Step S203: Sort the predicted egg production rate loss values ​​in descending order to generate an execution queue for priority control instructions.

[0069] The execution queue refers to the sequence of control instructions formed by sorting the predicted egg production rate loss values ​​in descending order. The larger the loss value, the higher the priority of the corresponding control instruction.

[0070] For example, the highest predicted loss in egg production rate due to excessive NH3 is 3.2%, followed by H2S at 2.5%, and finally CO2 at 1.8%. The generated execution queue is as follows: the first priority is to start the ventilation system to reduce the NH3 concentration; the second priority is to link the feed feeding system to add methionine preparation; and the third priority is to trigger the spray deodorization device to reduce the CO2 concentration.

[0071] Step S204: Call the device power consumption data in the device power consumption database to dynamically calculate the remaining load capacity of the distribution box.

[0072] The remaining load capacity of a distribution box refers to the current power load margin available for starting new equipment. It is calculated by subtracting the total power consumption of all currently operating equipment from the rated total capacity of the distribution box.

[0073] For example, if a distribution box has a rated capacity of 5kW, and the current lighting, water supply system and other basic equipment occupy a total of 1.2kW, the ventilation system is running and consumes 1.3kW, the current total load is 2.5kW, the calculated remaining load capacity of the distribution box is 2.5kW.

[0074] Step S205: Based on the remaining load capacity of the distribution box, start the control equipment in the order of the execution queue to satisfy: P1+P2+...+P k ≤P remain P k P represents the real-time power consumption of the k-th device to be started. remain This represents the current remaining available load capacity.

[0075] For example, if the current remaining load capacity is 2.5kW, the first device in the execution queue is a feed dispensing system with an instantaneous power consumption of 0.5kW, which is less than the remaining capacity, and it starts immediately. The second device is a spray deodorization device with a power consumption of 0.8kW, after which the remaining capacity becomes 1.7kW. The third device is a backup ventilation system with a power consumption of 1.3kW, which can still be started. If a device has a power consumption of 2.6kW, it will not start temporarily because it exceeds the remaining capacity.

[0076] Step S206: Initiate a delay compensation mechanism for the unexecuted execution queue.

[0077] The delay compensation mechanism refers to compensating for equipment delays by appropriately extending the operating time or increasing the operating intensity.

[0078] For example, increasing the spray cycle of a delayed-start spray deodorization device or extending the operating time of a ventilator.

[0079] By adopting the above technical solution, combined with an egg production performance prediction model to intelligently assess the level of environmental hazards, and simultaneously accurately matching the optimal control scheme from the equipment control strategy library, the solution automatically triggers tiered control commands. This solution significantly improves the accuracy of environmental control, optimizes equipment resource scheduling, avoids over- or under-control, and significantly improves poultry house environmental quality and breeding production efficiency.

[0080] This application discloses a device startup control method based on power load optimization. (Refer to...) Figure 3 The method includes: Step S301: Query the device power consumption database, identify the devices to be started in the execution queue whose start-up transient current exceeds N times the rated operating current, and extract the rated power of the devices to be started.

[0081] Transient current refers to the instantaneous current generated by the motor or electromagnetic components at the moment of startup of the equipment, which is higher than the normal operating current.

[0082] Rated operating current refers to the stable current of a device when it is running continuously under standard operating conditions.

[0083] For example, before execution, the system queries the device power consumption database and finds that the start-up transient current of the feed feeding system is 8A, while its rated operating current is 2A, which exceeds 4 times the threshold. Therefore, its rated power is extracted as 1.8kW.

[0084] Step S302: Calculate the minimum start-up time interval based on the rated power.

[0085] The minimum start-up time interval is the shortest time delay between the start-up of adjacent devices to avoid a sudden voltage drop in the power distribution system caused by the simultaneous start-up of multiple high-start-current devices. The minimum start-up time interval is calculated as: (Rated power of the device / Base power value of 1000 watts) × Base time constant of 50 milliseconds.

[0086] For example, for a feed feeding system with a rated power of 1.8kW, the minimum start-up time interval is calculated by the formula = (1800 / 1000) × 50 = 90 (milliseconds).

[0087] Step S303: Determine the minimum capacity requirement of the buffer capacitor bank based on the minimum start-up time interval and the equipment current parameters. The equipment current parameters include the start-up transient current and the rated operating current.

[0088] A buffer capacitor bank is a collection of capacitors connected in parallel in a power supply line to provide instantaneous current support and absorb the transient current surge during equipment startup.

[0089] The minimum capacity requirement refers to the minimum capacitance of the capacitor required to effectively suppress voltage fluctuations. The minimum capacity requirement is ≥ (equipment startup transient current - rated operating current) × minimum startup time interval / upper limit of allowable voltage fluctuation.

[0090] For example, if the transient current of the feed feeding system at startup is 8A, the rated operating current is 2A, the minimum startup time interval is 90 milliseconds, and the allowable voltage fluctuation limit is 11V, then the required capacitance is ≥ (8A-2A)×0.09s / 11V≈0.049F, which means that at least a buffer capacitor bank of 49000μF is required.

[0091] Step S304: Based on the minimum capacity requirement, detect the current fluctuation amplitude in real time during equipment startup.

[0092] Current fluctuation amplitude refers to the maximum instantaneous deviation between the actual current and the rated current during equipment startup.

[0093] Real-time detection refers to the continuous acquisition of current signals by a current sensor during device startup.

[0094] For example, when the minimum capacity requirement of the buffer capacitor bank is determined to be 50,000 μF, the current signal during the start-up process is collected in real time by the current sensor when the feed feeding system is started. It is monitored that the current rises from 2A to 8.2A at the moment of start-up, with a fluctuation range of 6.2A. This value is used to determine whether it exceeds the allowable range and to decide whether to adjust the subsequent capacitor configuration.

[0095] Step S305: When the current fluctuation exceeds the allowable upper limit, automatically increase the minimum capacity requirement of subsequent devices and update the device power consumption database.

[0096] The allowable upper limit refers to the preset safety threshold for current fluctuations, which is used to determine whether the startup process is abnormal.

[0097] For example, when the fluctuation of the starting current of the feed feeding system is detected to exceed the allowable upper limit of 6A, the original calculated minimum capacitance of 49000μF is increased to 60000μF, and this corrected value, together with the current starting current data, is updated to the device power consumption database.

[0098] By adopting the above technical solutions, dynamically optimizing equipment startup timing and intelligently configuring power buffer capacitor banks, combined with a real-time power monitoring and feedback mechanism, stable power supply is achieved under the coordinated operation of multiple devices. This solution effectively solves the risks of instantaneous impacts and overloads faced by traditional farm power systems, significantly improving power supply reliability and equipment lifespan while ensuring timely response to environmental control measures.

[0099] This application discloses a gas monitoring method based on sensor difference detection. (Refer to...) Figure 4 The method includes: Step 401: Calculate the difference in CO2 concentration between the electrochemical sensor and the infrared sensor in the gas detection device.

[0100] An electrochemical sensor is a detection device that generates a current signal based on the electrochemical reaction between a gas and an electrolyte, such as for detecting ammonia, hydrogen sulfide, and carbon dioxide.

[0101] Infrared sensors are devices that use the absorption characteristics of gases to infrared light of specific wavelengths to detect concentrations, such as those used to detect ammonia, hydrogen sulfide, and carbon dioxide.

[0102] The difference is calculated by simultaneously acquiring the CO2 concentration values ​​measured by the electrochemical sensor and the infrared sensor at the same time point, subtracting the concentration value measured by the electrochemical sensor from the concentration value measured by the infrared sensor, and taking the absolute value to obtain the difference between the two.

[0103] For example, at a monitoring point in a farm, an infrared sensor measured a CO2 concentration of 2900 ppm, while an electrochemical sensor measured a CO2 concentration of 2500 ppm. The difference between the two was calculated to be 400 ppm.

[0104] Step 402: Determine whether the difference is greater than the difference threshold and whether the duration exceeds the time threshold.

[0105] For example, if the difference of 400 ppm is continuously monitored and found to be maintained for 12 minutes, which meets the condition that the difference is greater than 300 ppm and the duration is more than 10 minutes, then proceed to the next judgment process.

[0106] Step 403: If yes, determine that the infrared sensor is contaminated by particulate matter in the poultry house and trigger the optical path self-cleaning program. Particulate matter in the poultry house includes dust, feather debris, or water mist.

[0107] The optical path self-cleaning program refers to activating the cleaning mechanism built into the infrared sensor.

[0108] For example, when the system detects that the difference in CO2 concentration between the infrared sensor and the electrochemical sensor has been exceeding 300 ppm for 12 minutes, it determines that the optical path of the infrared sensor is contaminated by dust or feather debris deposits in the farm, and then starts the built-in micro fan to blow and clean it for 30 seconds.

[0109] Step 404: Use the detection data from the electrochemical sensor as the master control data, and add confidence level labels to the data detected by the infrared sensor.

[0110] Master control data refers to sensor data that is preferentially used as the basis for control decisions among multiple sensors.

[0111] Confidence rating refers to the weighting labels attached to the sensor output data.

[0112] For example, after determining that the infrared sensor is contaminated by particulate matter in the poultry house, the CO2 concentration of 2500 ppm measured by the electrochemical sensor is used as the main control data, while the CO2 concentration of 2900 ppm output by the infrared sensor is labeled with an 80% confidence level, so that its weight in the data fusion is reduced.

[0113] Step 405: If not, remove the confidence level marker and restore the data fusion output of the electrochemical sensor and the infrared sensor.

[0114] Removing the confidence level label means canceling the downweighting of sensor data and restoring it to its normal weight.

[0115] Data fusion output refers to the process of combining measurement results from different types of sensors with algorithms to generate more accurate and stable final concentration values.

[0116] For example, if the difference in CO2 concentration between the electrochemical sensor and the infrared sensor is detected to be 200 ppm and does not last for more than 10 minutes, the infrared sensor is determined to be working normally, its "80% confidence level" mark is automatically removed, it is restored to 100% confidence level, and the data is re-fused to output the final CO2 concentration value.

[0117] By adopting the above technical solution, a dynamic reliability assessment mechanism is established by comparing the detection differences between the electrochemical sensor and the infrared sensor in real time, and a self-cleaning function for the optical path is added, enabling reliable monitoring in polluted environments in aquaculture farms. This solution ensures data continuity and significantly improves the system's anti-interference capability.

[0118] This application discloses a gas monitoring method based on sensor self-diagnosis. (Refer to...) Figure 5 The method includes: Step 501: Obtain gas concentration data from the electrochemical sensor in the most recent time period.

[0119] For example, CO2 concentration values ​​measured by an electrochemical sensor were collected every 30 seconds during the most recent half hour.

[0120] Step 502: If the gas concentration data continues to deviate from the reference value, and the gas concentration data exceeds the preset deviation threshold, and the duration of the gas concentration data exceeding the preset deviation threshold is greater than the preset duration, then the electrochemical sensor is determined to be invalid.

[0121] The baseline value refers to the stable concentration reference value measured under normal equipment calibration conditions.

[0122] For example, if the CO2 concentration measured by the electrochemical sensor remains at 3100 ppm for 30 minutes, while the reference value is 2800 ppm, the deviation is 300 ppm and lasts for more than 15 minutes, then the electrochemical sensor is deemed invalid.

[0123] Step 503: Obtain gas concentration data for the most recent time period from the infrared sensor and calculate the average concentration value as temporary baseline data.

[0124] The average concentration value is calculated by acquiring multiple sets of gas concentration data continuously collected by the infrared sensor within the most recent time period. A fixed number of the most recent continuous data points are used as a sliding window, and the average value of the data within the window is calculated in real time. As new data is added, the window is continuously moved forward and the average value is updated, thus obtaining a dynamic temporary benchmark value.

[0125] For example, if the infrared sensor collects CO2 data every 30 seconds over the past 30 minutes, totaling 60 points, and a sliding window is used to take the average of the most recent 20 points, the temporary baseline value is calculated to be 2820 ppm.

[0126] Step 504: Activate the backup sensor and cross-validate the data detected by the backup sensor in real time with the temporary reference data.

[0127] Backup sensors refer to independent sensors that are pre-deployed at the same or nearby detection points and are normally in standby mode.

[0128] Cross-validation refers to determining consistency by comparing the measurement results of two independent sensors in the same environment.

[0129] For example, the backup sensor at the detection point is activated, and the CO2 concentration is initially measured at 2800 ppm. This is compared with the temporary reference value of 2820 ppm provided by the infrared sensor, and then the verification process begins.

[0130] Step 505: If the difference in cross-validation is less than the cross-validation threshold, generate a validation pass signal.

[0131] A verification pass signal is a logic signal that indicates the backup sensor data is reliable and ready for use.

[0132] For example, if the backup sensor measures 2800 ppm and the temporary reference value is 2820 ppm, the difference is 20 ppm, which is less than the 50 ppm threshold. A verification pass signal is then generated to confirm that the backup sensor is working properly.

[0133] Step 506: In response to the verification pass signal, mark the status of the corresponding detection point of the backup sensor as emergency mode and trigger an early warning signal, which includes a location code and a confidence index.

[0134] Emergency mode refers to a special operating state in which a backup sensor takes over when the main sensor fails.

[0135] Warning signals are information that includes fault location information and data reliability assessment, used to notify administrators to handle the situation promptly.

[0136] For example, the detection point numbered A03 is marked as "emergency mode" and an early warning signal is sent to the administrator terminal, including the location code A03 and the confidence index of 95%, indicating that the detection point has been switched to the backup sensor operation.

[0137] Step 507: Based on the early warning signal, generate information on recommended maintenance measures.

[0138] Repair measures refer to maintenance suggestions automatically generated based on the type of fault.

[0139] For example, a maintenance prompt is generated based on the warning signal: "The electrochemical sensor at detection point A03 is suspected of being malfunctioning. It is recommended to check the electrolyte status on-site or replace the sensor module, and record the maintenance log."

[0140] By adopting the above technical solutions, an electrochemical sensor effectiveness determination mechanism, an infrared sensor sliding window benchmark algorithm, and a backup sensor cross-validation process were established, constructing a complete self-diagnosis system for environmental monitoring faults. This solution achieves reliable data transmission and intelligent verification, significantly improving the stability and data accuracy of the livestock farm gas monitoring system.

[0141] This application discloses a risk warning method based on predictive analysis. (Refer to...) Figure 6The method includes: Step 601: Collect gas concentration data from multiple monitoring points in the farm in real time. The gas concentration data includes the concentration value and the rate of change.

[0142] For example, in a farm, six monitoring points are set up, and the system collects the NH3 concentration value of each point every minute. If at monitoring point A, the current NH3 concentration is 12 ppm, and the concentrations in the previous 5 minutes were 8, 9, 10, 11, and 12 ppm respectively, the rate of change is calculated to be +1 ppm / minute.

[0143] Step 602: Compare and analyze the gas concentration data with historical gas concentration data to predict the gas concentration change trend of multiple detection points in the next monitoring cycle and obtain the prediction results.

[0144] The prediction result refers to the predicted gas concentration and its direction of change for the next monitoring period based on the model output.

[0145] The gas concentration data is aligned with historical gas concentration data over time, and the concentration value, rate of change, and environmental correlation features are extracted as inputs and fed into a pre-trained model. Based on the learned historical change patterns, the model outputs the concentration prediction value for the next monitoring period, thereby obtaining the prediction result of the gas concentration change trend.

[0146] For example, retrieving NH3 concentration data from monitoring point A over the past 7 days under the same age and ventilation mode reveals a historical average increase of 0.5 ppm / hour. The current rate of change is 1 ppm / minute, deviating from the historical pattern. Based on the current data, the model predicts that the NH3 concentration at this point will reach 72 ppm in the next hour, exceeding the normal level.

[0147] Step 603: Based on the amount by which the prediction result exceeds the risk threshold, set a risk level for the monitoring area corresponding to the detection point. The risk levels include high risk, medium risk, and low risk.

[0148] Risk level refers to the classification of levels based on the degree to which the predicted concentration exceeds the risk threshold. High risk generally exceeds the risk threshold by more than 20%, medium risk generally exceeds the risk threshold but does not exceed it by more than 20%, and low risk generally does not reach the risk threshold.

[0149] For example, at detection point A, the NH3 risk threshold is 20 ppm, and the model predicts the concentration for the next hour to be 25 ppm, which exceeds the threshold by 25% and is considered high risk; at another detection point B, the predicted concentration is 23 ppm, which exceeds the threshold by 15% and is considered medium risk; at detection point C, the predicted concentration is 18 ppm, which does not exceed the threshold and is considered low risk.

[0150] Step 604: Send a warning signal based on the prediction results and risk level.

[0151] A warning signal is a type of information used to indicate environmental anomalies. It includes information such as risk level, location of occurrence, predicted concentration, and recommended measures. It can be sent to the administrator via audible and visual alarms, SMS push notifications, or system pop-ups.

[0152] For example, an early warning signal is sent to the farm administrator's terminal to trigger the corresponding response mechanism.

[0153] By adopting the above-mentioned technical solution, combining real-time monitoring with historical data analysis, a dynamic risk assessment is established, enabling accurate prediction and tiered early warning of environmental risks. This solution can identify potential risk areas in advance and achieve differentiated early warning through a three-tiered risk classification, significantly improving the initiative and accuracy of environmental risk prevention and control in livestock farms.

[0154] This application discloses a sensor intelligent calibration method based on anomaly detection. (Refer to...) Figure 7 The method includes: Step 701: Based on the real-time gas concentration data, when the growth rate of the target detection point in a single sampling cycle exceeds the average growth rate of adjacent points, a freeze command is generated. The freeze command includes the target detection point identifier, the abnormal increase value, and the average baseline value of adjacent points.

[0155] A freeze command is a temporary control signal used to mark a potential anomaly in the data of a certain detection point and suspend its participation in fusion calculations or control decisions.

[0156] For example, at monitoring point M04 in the aquaculture farm, the NH3 concentration increased from 10 ppm to 13 ppm, with an increase rate of 3 ppm / min. The increase rates of its neighboring points M03 and M05 were 1.1 ppm / min and 0.9 ppm / min, respectively, with an average of 1.0 ppm / min. The increase rate of M04 was significantly higher than that of its neighbors, generating a freeze command, which included: the target monitoring point identifier M04, the abnormal increase value of 3 ppm / min, and the average baseline value of 1.0 ppm / min for neighboring points.

[0157] Step 702: Based on the freeze command, retrieve the historical data fluctuation range of the target detection point and compare it with the gas concentration data.

[0158] Historical data fluctuation range refers to the concentration change range calculated based on data collected from the target detection point over a period of time, such as 7 days, under normal operating conditions.

[0159] For example, the NH3 concentration data for the past 7 days at point M04 was retrieved, and the normal fluctuation range was found to be 8–12 ppm. The current concentration is 13 ppm, which exceeds the upper limit, and the anomaly detection process is initiated.

[0160] Step 703: If the gas concentration data continues to exceed the upper limit of the historical data fluctuation range, output a device fault signal.

[0161] Equipment fault signals are logic signals that indicate that the sensor at the detection point may be contaminated, aged, or have circuit problems that cause output distortion and require maintenance.

[0162] For example, the NH3 concentration at point M04 was 13.2 ppm, 13.5 ppm, and 13.8 ppm in the subsequent three consecutive sampling periods, all of which were higher than the upper limit of 12 ppm. The system determined this to be a continuous abnormality and output a device fault signal.

[0163] Step 704: In response to the equipment fault signal, send a data disable command to the administrator terminal and at the same time issue a forced calibration command to the target detection point. The forced calibration command includes the purging pressure and standard gas concentration.

[0164] The data disable command is a command that suspends the use of the detection point data.

[0165] A forced calibration command is an instruction that triggers the automatic calibration process of a sensor.

[0166] Purging pressure refers to the pressure of compressed airflow used to remove dust, water vapor, or residual gas from the sensor's air intake channel.

[0167] Standard gas concentration refers to a reliable concentration value derived from other normally functioning sensors in the same monitoring area.

[0168] For example, a message is pushed to the administrator's mobile phone: "Detection point M04 data is abnormal and has been disabled." At the same time, a forced calibration command is issued to the M04 device, which includes a purge pressure of 80 kPa and 10 ppm NH3 obtained by fusing data from adjacent normal sensors as a standard gas concentration reference value, and initiates the automatic cleaning and calibration program.

[0169] Step 705: Obtain standard data, which is calibrated gas concentration data.

[0170] Standard data refers to the gas concentration data that the sensor re-collects after completing mandatory calibration.

[0171] For example, after the calibration process is completed at point M04, the ambient gas is collected again, and the NH3 concentration is measured to be 10.2 ppm. This data is used as standard data for subsequent verification.

[0172] Step 706: When the number of samplings of the standard data reaches the standard threshold and the standard data returns to the historical data fluctuation range, send a data recovery command to the administrator terminal.

[0173] A data recovery command is a signal that reactivates the data from that detection point, restoring its participation in fusion computing and control decisions.

[0174] For example, after collecting data from point M04 for calibration five times consecutively, the results are 10.0, 10.2, 10.1, 9.9, and 10.3 ppm, all within the range of 8 to 12 ppm, which meets the recovery conditions. A notification will be sent to the administrator that "point M04 calibration is complete and data has been recovered".

[0175] By adopting the above technical solutions, including real-time data anomaly detection, historical data comparison and analysis, and mandatory calibration processes, a complete equipment status monitoring system has been constructed. This solution significantly improves the reliability and data accuracy of the monitoring system, providing continuous and stable data support for farm environmental management and effectively avoiding the environmental control failures caused by equipment malfunctions in traditional monitoring systems.

[0176] Based on the same inventive concept, embodiments of this application provide an optimization system based on gas concentration regulation, the system comprising: Module 801 is used to acquire gas concentration data and a gas concentration-egg production rate correlation model. The memory 802 is used to store the program of the optimization method based on gas concentration regulation; The processor 803 can load and execute the program in the memory to implement the optimization method based on gas concentration regulation.

[0177] By adopting the above technical solution, the monitoring module collects gas concentration data of the farm in real time, the processor dynamically executes the trend prediction algorithm, and the memory continuously optimizes the risk assessment model, realizing intelligent management of the entire process from environmental monitoring to graded early warning. While ensuring the accuracy of early warning, it significantly improves the efficiency of risk prevention and control, providing an intelligent and reliable solution for the environmental management of modern farms.

[0178] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0179] This application provides a computer-readable storage medium storing a computer program that can be loaded and executed by a processor, which is an optimization method based on gas concentration regulation.

[0180] Computer storage media include, for example, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media that can store program code.

[0181] Based on the same inventive concept, embodiments of this application provide a smart terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded and executed by the processor, which is an optimization method based on gas concentration regulation.

[0182] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0183] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. An optimization method based on gas concentration regulation, characterized in that, include: Gas concentration data, including ammonia, hydrogen sulfide and carbon dioxide, is collected in real time using gas detection devices in the farm. When the gas concentration data exceeds the safety threshold, the predicted egg production rate is obtained based on the prediction results output by the gas concentration-egg production rate correlation model. A graded control mechanism is activated based on the predicted egg production rate; After the graded control mechanism is activated, it is determined whether the gas concentration data meets the preset requirements; If not, if the gas concentration data is detected to exceed the safety threshold, or the rate of decrease of the gas concentration data is lower than the rate threshold, the sampling frequency and detection accuracy of the gas detection device are increased; the spatial distribution density of the gas detection device is increased; and the equipment status corresponding to the graded control mechanism is adjusted. If the gas concentration data is detected to be within the safety threshold and the rate of decrease of the gas concentration data is not lower than the rate threshold, the graded control mechanism is turned off.

2. The optimization method based on gas concentration control according to claim 1, characterized in that, The predicted egg production rate activation tiered control mechanism also includes: Establish a device power consumption database, which is used to store power consumption data of ventilation system, spray deodorization device and feed feeding system; When the gas concentration data is detected to synchronously exceed the safety threshold, the predicted egg production rate loss value corresponding to each gas exceeding the standard is calculated according to the gas concentration-egg production rate correlation model. The predicted egg production rate loss values ​​are sorted in descending order to generate an execution queue for priority control instructions. The remaining load capacity of the distribution box is dynamically calculated by calling the device power consumption data in the device power consumption database. Based on the remaining load capacity of the distribution box, the control equipment is activated in the order of the execution queue to satisfy: P1+P2+...+P k ≤P remain P k P represents the real-time power consumption of the k-th device to be started. remain This represents the current remaining available load capacity. A delay compensation mechanism is initiated for the execution queue that has not yet been executed.

3. The optimization method based on gas concentration control according to claim 2, characterized in that, The step of starting the control equipment according to the remaining load capacity of the distribution box and in the execution queue sequence includes: Query the device power consumption database to identify devices in the execution queue whose startup transient current exceeds N times the rated operating current, and extract the rated power of the devices to be started; Calculate the minimum start-up time interval based on the rated power; The minimum capacity requirement of the buffer capacitor bank is determined based on the minimum start-up time interval and the equipment current parameters, wherein the equipment current parameters include the start-up transient current and the rated operating current. Based on the minimum capacity requirement, the current fluctuation amplitude is detected in real time during equipment startup; When the current fluctuation exceeds the allowable upper limit, the minimum capacity requirement of subsequent devices is automatically increased and the device power consumption database is updated.

4. The optimization method based on gas concentration control according to claim 1, characterized in that, Gas detection devices include at least an electrochemical sensor and an infrared sensor; When the gas concentration data exceeds a safety threshold, increasing the sampling frequency and detection accuracy of the gas detection device also includes: Calculate the difference in CO2 concentration between the electrochemical sensor and the infrared sensor in the gas detection device; Determine whether the difference is greater than a difference threshold and whether the duration exceeds a time threshold; If so, it is determined that the infrared sensor is contaminated by particulate matter in the poultry house, triggering the optical path self-cleaning program. The particulate matter in the poultry house includes dust, feather debris, or water mist. The detection data of the electrochemical sensor is used as the master control data, and a confidence level label is added to the data detected by the infrared sensor. If not, remove the confidence level marker and restore the data fusion output of the electrochemical sensor and the infrared sensor.

5. The optimization method based on gas concentration control according to claim 4, characterized in that, After using the detection data from the electrochemical sensor as the master control data, the process includes: Acquire the gas concentration data of the electrochemical sensor in the most recent time period; If the gas concentration data continues to deviate from the reference value, and the gas concentration data exceeds a preset deviation threshold, and the duration of the gas concentration data exceeding the preset deviation threshold is greater than a preset duration, then the electrochemical sensor is determined to be invalid. The average concentration value is calculated based on the gas concentration data acquired by the infrared sensor within the most recent time period and used as temporary reference data. Activate the backup sensor and cross-validate the real-time data detected by the backup sensor with the temporary reference data; If the difference in the cross-validation is less than the cross-validation threshold, a validation pass signal is generated; In response to the verification pass signal, the status of the detection point corresponding to the backup sensor is marked as emergency mode, and an early warning signal is triggered, the early warning signal including a location code and a confidence index; Based on the warning signal, information on recommended maintenance measures is generated.

6. The optimization method based on gas concentration control according to claim 1, characterized in that, The method further includes: The gas concentration data at multiple monitoring points in the farm are collected in real time, and the gas concentration data includes the concentration value and the rate of change. By comparing and analyzing the gas concentration data with historical gas concentration data, the gas concentration change trend of the multiple detection points in the next monitoring cycle is predicted, and the prediction result is obtained. Based on the amount by which the prediction result exceeds the risk threshold, a risk level is set for the monitoring area corresponding to the detection point, and the risk level includes high risk, medium risk and low risk. Based on the prediction results and the risk level, a warning signal is sent.

7. The optimization method based on gas concentration control according to claim 6, characterized in that, The method further includes: Based on the real-time detected gas concentration data, when the growth rate of the target detection point in a single sampling cycle exceeds the average growth rate of adjacent points, a freeze command is generated. The freeze command includes the target detection point identifier, the abnormal increase value, and the average baseline value of adjacent points. Based on the freeze command, the historical data fluctuation range of the target detection point is retrieved and compared with the gas concentration data; If the gas concentration data continues to exceed the upper limit of the historical data fluctuation range, a device fault signal will be output. In response to the equipment fault signal, a data disable command is sent to the administrator terminal, and a forced calibration command is issued to the target detection point. The forced calibration command includes purge pressure and standard gas concentration. Acquire standard data, which is calibrated gas concentration data; When the number of samplings of the standard data reaches the standard threshold and the standard data returns to the historical data fluctuation range, a data recovery command is sent to the administrator terminal.

8. An optimization system based on gas concentration regulation, characterized in that, The system is used to execute the optimization method based on gas concentration regulation as described in any one of claims 1 to 7, comprising: The acquisition module is used to acquire gas concentration data and the gas concentration-egg production rate correlation model; A memory for storing the program of the optimization method based on gas concentration regulation; The processor and the program in the memory can be loaded and executed by the processor to implement the optimization method based on gas concentration regulation.

9. A smart terminal, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and execute the method as described in any one of claims 1 to 7.

Images