Mobile intelligent fumigation anti-interference control system

Abstract

The invention discloses a mobile intelligent fumigation anti-interference control system, which relates to the technical field of intelligent fumigation and comprises a data acquisition module, an anti-interference processing module, a fumigation effect evaluation module, an intelligent control module and a remote interaction module. In the system, the data acquisition module performs multi-measurement-point real-time acquisition on the temperature, humidity, pressure and fumigation gas concentration in the fumigation room, and transmits data through a wired or wireless communication interface; the anti-interference processing module is used for suppressing interference signals by adopting an algorithm of fusing Kalman filtering and wavelet denoising and outputting stable and effective monitoring data; the fumigation effect evaluation module is used for calculating a fumigation effect comprehensive index based on the effective monitoring data so as to judge whether fumigation reaches the standard or not, and can adaptively adjust a standard reaching interval according to the type of a fumigation object; the intelligent control module is used for receiving the fumigation effect evaluation result, dynamically adjusting temperature, humidity and gas concentration parameters in the fumigation process and dynamically adjusting a model weight coefficient according to the real-time evaluation result.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent fumigation technology, in particular to a mobile intelligent fumigation anti-interference control system. BACKGROUND

[0002] Fumigation is a kind of technical means that uses toxic gases or volatile chemical agents to kill harmful organisms by gas diffusion and penetration in a closed space such as a warehouse, tent, soil, container, etc. The core of fumigation is to use gaseous molecules of fumigation agents to act on the respiratory system or enzyme system of harmful organisms to destroy their physiological functions to achieve the purpose of prevention and control.

[0003] At present, the traditional system mainly collects temperature and humidity, fumigation gas concentration at single point or a few measuring points, and the collection dimension is limited. The fumigation environment easily disturbs the sensor, and the collected data has large noise and poor accuracy. At the same time, there is a lack of efficient fusion filtering algorithm, which cannot fully suppress complex interference such as environmental fluctuations and sensor self-noise, resulting in that the stability and reliability of the monitoring data are difficult to support subsequent accurate analysis. The traditional fumigation parameters are controlled manually or by simple fixed value control, which cannot adaptively adjust the key parameters such as temperature, humidity and gas concentration according to the real-time fumigation effect, and it is difficult to balance and optimize between ensuring the fumigation effect and reducing energy consumption.

[0004] Therefore, the mobile intelligent fumigation anti-interference control system is proposed to solve the above problems. SUMMARY

[0005] The main purpose of the present application is to provide a mobile intelligent fumigation anti-interference control system to solve the problems raised in the above background.

[0006] To achieve the above purpose, the technical scheme adopted by the present application is as follows: a mobile intelligent fumigation anti-interference control system, the system comprises a data acquisition module, an anti-interference processing module, a fumigation effect evaluation module, an intelligent control module and a remote interaction module; The data acquisition module is used for real-time acquisition of temperature and humidity, pressure and fumigation gas concentration in the fumigation warehouse at multiple measuring points, and the collected data is transmitted through a wired or wireless communication interface; The anti-interference processing module suppresses the interference signal by using a fusion filtering algorithm based on the collected data, and outputs stable effective monitoring data; The fumigation effect evaluation module constructs a fumigation effect evaluation model based on the effective monitoring data, calculates a fumigation effect comprehensive index, and compares it with a preset threshold to determine whether the fumigation is up to standard; The intelligent control module receives the fumigation effect evaluation result, constructs a fumigation parameter optimization control model, and dynamically adjusts the temperature, humidity and gas concentration parameters in the fumigation process; The remote interaction module is used to interact with the remote monitoring platform to collect data, anti-interference results, fumigation effect evaluation results and control commands, and supports multi-terminal access and control.

[0007] Preferably, the data acquisition module includes a multi-point acquisition unit, a communication unit, and a synchronization unit; The multi-point acquisition unit is used to simultaneously acquire temperature, humidity, pressure, and fumigation gas concentration data at at least three detection points in the fumigation chamber, and the acquisition frequency is configurable. The communication unit supports multiple access methods such as wired, WiFi, 4G or 5G, and transmits the collected data to the anti-interference processing module in real time; The synchronization unit is used to synchronize and calibrate the acquisition time of multiple measurement points to ensure the time consistency of multi-source data.

[0008] Preferably, the anti-interference processing module employs a filtering algorithm that combines Kalman filtering and wavelet denoising. The specific processing steps are as follows: Step 1: Perform preliminary denoising on the collected data using wavelet denoising to obtain preliminary denoised data; Step 2: Further filter the initially denoised data using Kalman filtering. The state equation is: X k =AX k-1 +BU k +W k ; The observation equation is: Z k =HX k +V k ; Among them, X k Let Z be the system state at time k. k Let W be the observation value at time k, A, B, and H be the state transition, control input, and observation matrix, respectively. k V k For process noise and observation noise; Step 3: Output the effective monitoring data after fusion filtering.

[0009] Preferably, the anti-interference processing module can adaptively adjust the process noise covariance matrix Q and the observation noise covariance matrix R of the Kalman filter according to the noise characteristics of the collected data; The adjustment rule is as follows: when an increase in noise variance is detected, the corresponding element value of Q or R is increased accordingly.

[0010] Preferably, the fumigation effect evaluation model of the fumigation effect evaluation module is implemented by calculating the comprehensive fumigation effect index E, and the calculation formula is: Among them, T实际 T 基准 T 允许波动 For actual, reference, and permissible temperature fluctuations, RH 实际 RH 基准 RH 允许波动 For actual, benchmark, and permissible humidity fluctuations, The maximum value is 1; When E is within the preset acceptable range, the fumigation is deemed to be compliant; otherwise, it is deemed non-compliant.

[0011] Preferably, the preset compliance range of the fumigation effect evaluation module can be adaptively adjusted according to the type of the fumigation object; Using the built-in fumigation object database, when different fumigation objects are selected, the corresponding C is automatically matched. 标准 T 基准 RH 基准 The parameters are then used to adjust the target range.

[0012] Preferably, the fumigation parameter optimization control model of the intelligent control module is a multi-objective optimization model, and the objective function is: minF=α·E energy -β·(1-R 达标 ), Where α + β = 1 is the weighting coefficient, and both α and β are non-negative numbers, E energy For fumigation energy consumption, R 达标 To ensure the fumigation effect meets the standards; The constraints include temperature constraint T. min ≤T≤T max Humidity constraint RH min ≤RH≤RH max Gas concentration constraint C min ≤C≤C max ; By solving this model, dynamic adjustment parameters for temperature, humidity, and gas concentration are output.

[0013] Preferably, the intelligent control module can dynamically adjust the weight coefficients α and β in the multi-objective optimization model based on the real-time evaluation results of the fumigation effect evaluation module; When the fumigation effect is not up to standard, increase the value of β and decrease the value of α to prioritize ensuring the fumigation effect meets the standard.

[0014] Preferably, the remote interaction module includes a data uploading unit, an instruction receiving unit, and a multi-terminal adaptation unit; The data uploading unit uploads the collected data, the data after anti-interference, the fumigation effect evaluation results, and the control parameters to the remote monitoring platform in encrypted form in real time. The instruction receiving unit receives control instructions and parameter configuration instructions issued by the remote monitoring platform; The multi-terminal adapter unit supports access to the system via web pages or apps from multiple terminals such as computers, tablets, and mobile phones, enabling data viewing and remote control.

[0015] Preferably, the multi-point acquisition unit, anti-interference processing module, and some intelligent control modules of the system are integrated inside a cabinet with casters for easy on-site movement; The cabinet is also equipped with a backup power unit, which can support the system to run continuously for at least 2 hours when the external power supply is interrupted.

[0016] The present invention has the following beneficial effects: 1. In this invention, the data acquisition module synchronously collects multi-dimensional data such as temperature, humidity, pressure, and fumigation gas concentration in the fumigation chamber from multiple measurement points, providing the system with real-time and comprehensive raw information input, ensuring that subsequent modules can conduct analysis based on real-world scenarios. The anti-interference processing module adopts a fusion algorithm of wavelet denoising and Kalman filtering. First, wavelet denoising is used to initially eliminate coarse-level interference such as sensor noise and environmental electromagnetic interference, and then Kalman filtering is used to finely optimize the remaining fine-level errors and model biases. The two work together to ensure both the richness of multi-source data and the high reliability of the data, providing solid data support for the accuracy of fumigation effect evaluation and the scientific nature of intelligent control, and avoiding misjudgment of effects and parameter misadjustment in subsequent stages due to data distortion.

[0017] 2. In this invention, the fumigation effect evaluation module constructs a comprehensive index model based on the effective data after anti-interference. It quantifies whether fumigation meets standards from dimensions such as the coverage of fumigation gas concentration to the standard and the deviation of temperature and humidity from the benchmark. This transforms the complex fumigation effect into intuitive compliance results and a comprehensive index, providing a clear decision-making basis for the intelligent control module. The intelligent control module uses this evaluation result as its core to construct a multi-objective optimization model, balancing fumigation energy consumption and the compliance rate, and dynamically adjusting parameters such as temperature, humidity, and gas concentration. When the evaluation shows that the effect is not up to standard, the model prioritizes increasing the weight of the compliance rate, pushing parameters towards ensuring the effect. When the effect continues to meet standards, it focuses on reducing energy consumption. This closed-loop collaboration of evaluation feedback and intelligent control ensures efficient killing of harmful organisms during fumigation operations while avoiding energy waste, achieving precise, energy-saving, and intelligent control of the fumigation process.

[0018] 3. In this invention, the remote interaction module serves as an interaction bridge between the system and the outside world. The data upload unit synchronizes the raw data from the data acquisition module, the effective data after anti-interference processing, the index and compliance results from the fumigation effect evaluation module, and the dynamic parameters from the intelligent control module to the remote monitoring platform in encrypted form in real time, enabling the supervisor to fully grasp the fumigation process without being physically present on-site. The instruction receiving unit can receive control instructions and parameter configuration instructions issued by the platform and forward them to the corresponding modules for execution. The multi-terminal adaptation unit supports access via web pages or apps from multiple devices such as computers, tablets, and mobile phones, allowing operators to view data curves, review evaluation reports, and remotely adjust parameters anytime, anywhere. In collaboration with other modules, it completely breaks down the limitations of on-site operation and close-range supervision, improves the flexibility of fumigation operations, enhances the convenience and timeliness of supervision, and enables the entire fumigation system to operate efficiently in a remote and multi-terminal mode. Attached Figure Description

[0019] Figure 1 This is a framework diagram of the mobile intelligent fumigation anti-interference control system of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Please see Figure 1 The present invention provides a technical solution: a mobile intelligent fumigation anti-interference control system, the system including a data acquisition module, an anti-interference processing module, a fumigation effect evaluation module, an intelligent control module and a remote interaction module; the data acquisition module is used to collect temperature, humidity, pressure and fumigation gas concentration in the fumigation chamber in real time from multiple measurement points, and transmit the collected data through a wired or wireless communication interface; The anti-interference processing module uses a fusion filtering algorithm to suppress interference signals based on the collected data and outputs stable and effective monitoring data. The fumigation effect evaluation module constructs a fumigation effect evaluation model based on effective monitoring data, calculates the comprehensive index of fumigation effect, and compares it with a preset threshold to determine whether the fumigation meets the standards. The intelligent control module receives the fumigation effect evaluation results, constructs a fumigation parameter optimization control model, and dynamically adjusts the temperature, humidity, and gas concentration parameters during the fumigation process. The remote interaction module is used to interact with the remote monitoring platform to collect data, anti-interference results, fumigation effect evaluation results and control commands, and supports multi-terminal access and control.

[0022] The data acquisition module includes a multi-point acquisition unit, a communication unit, and a synchronization unit; The multi-point data acquisition unit is used to simultaneously collect temperature, humidity, pressure, and fumigation gas concentration data at at least three detection points within the fumigation chamber. The acquisition frequency is configurable. High-precision digital sensors are used for temperature and humidity, piezoresistive sensors are used for pressure, and fumigation gas concentration sensors are used to collect fumigation gas concentration data. When the acquisition frequency f is configured, the acquisition period T and the acquisition frequency f satisfy the following relationship: The communication unit supports multiple access methods such as wired, WiFi, 4G or 5G, and transmits the collected data to the anti-interference processing module in real time. The synchronization unit is used to synchronize and calibrate the acquisition time of multiple measurement points, ensuring the time consistency of multi-source data and providing a unified time reference for subsequent anti-interference and effect evaluation. Time synchronization is achieved using the Network Time Protocol (NTP). NTP achieves millisecond-level synchronization accuracy in a local area network environment, with the time difference Δt satisfying: Δt = t i -t ref , where t ref t is the standard time returned by the NTP server. i This is the local time of a certain measurement point acquisition unit; the synchronization unit adjusts the frequency compensation or phase jump of the local clock to make Δt approach 0, and finally controls the error of the timestamps of multiple measurement points within 10ms, so as to avoid the misalignment of multiple source data at the same physical moment due to time asynchrony and ensure the accuracy of subsequent data processing.

[0023] The anti-interference processing module adopts a filtering algorithm that combines Kalman filtering and wavelet denoising. The specific processing steps are as follows: Step 1: Perform preliminary denoising on the collected data through wavelet denoising to obtain preliminary denoised data; Specifically, wavelet decomposition is first performed on the collected raw data (using temperature data T). raw Taking (n) as an example, where n is the sampling point number), wavelet decomposition and reconstruction are performed to achieve noise reduction. The db4 wavelet is selected, and the decomposition level is set to 3 levels. T raw (n) is decomposed into approximation coefficients (denoted as cA, reflecting the low-frequency trend of temperature, i.e., the long-term variation law) and detail coefficients (denoted as cD1, cD2, cD3, reflecting the high-frequency details of temperature; noise is mainly concentrated in the detail coefficients). The mathematical essence of wavelet decomposition is to convolve and downsample the signal using a low-pass filter h and a high-pass filter g. The approximation coefficients cA of the j-th layer decomposition are... j and detail coefficient cD j satisfy: Where cA0(n)=T raw(n), where h is the coefficient of the low-pass filter and g is the coefficient of the high-pass filter. Downsampling is achieved by taking even index values, which halves the amount of data. Since the noise is mainly concentrated in the detail coefficients, the cD of each detail coefficient is calculated. j A soft thresholding function is used, and the formula is: Where ω j These are the original wavelet coefficients. The processed wavelet coefficients, λ is the threshold, and can be determined using heuristic rules. Let σ be the noise standard deviation and N be the signal length; perform soft thresholding on each detail coefficient cD1, cD2, cD3, while keeping the approximation coefficient cA unchanged. Using the processed approximation coefficients cA and the processed detail coefficients The preliminarily denoised temperature data T is obtained through wavelet reconstruction. wavelet (n), the formula is: Starting from the top-level decomposition (level 3), the data is reconstructed layer by layer, ultimately yielding cA0(n) = T. wavelet (n); Similarly, the humidity, pressure, and fumigation gas concentration data are processed through wavelet decomposition, thresholding, and wavelet reconstruction to obtain their respective preliminary denoised data.

[0024] Step 2: Further filter the initially denoised data using Kalman filtering: State equation: X k =AX k-1 +BU k +W k ; Observation equation: Z k =HX k +V k ; Among them, X k Let Z be the system state at time k. k Let W be the observation value at time k, A, B, and H be the state transition, control input, and observation matrix, respectively. k V k For process noise and observation noise; Kalman filtering iteratively optimizes the estimated system state through two stages: prediction and update. 1. Prediction Stage: Based on the state estimate at time k-1, predict the state at time k and the error covariance: (1). Prior state estimation (predicting the state at time k): (2). Prior error covariance (the degree of uncertainty in the predicted state) P k∣k-1 =AP k-1∣k-1 A T +Q; Among them, P k-1∣k-1 The posterior error covariance at time k-1 reflects the reliability of the state estimate at the previous time step.

[0025] 2. Update phase: Combining the observation value Z at time k k The prediction results are then corrected to obtain the posterior estimate: (1). Kalman gain (the weight that balances prediction uncertainty and observation uncertainty): K k =P k∣k-1 H T HP k∣k-1 H T +R) -1 ; K k The larger the value, the stronger the correction effect of the observation on the state estimate; conversely, the smaller the value, the higher the reliability of the prediction. (2). Posterior state estimation (corrected state at time k): To observe the residuals, which reflect the deviation between observed and predicted values, K is used. k Adjust the correction range; (3) Posterior error covariance (the degree of uncertainty in the corrected state estimate): P k∣k =(IK k H)P k∣k-1 , where I is the identity matrix.

[0026] Taking temperature data as an example, the final output of the effective monitored temperature is Similarly, Kalman filtering is performed on the preliminary noise-reduced data of humidity, pressure, and fumigation gas concentration to obtain all valid monitoring data.

[0027] Step 3: The temperature, humidity, pressure, and fumigation gas concentration data after wavelet denoising and Kalman filtering fusion processing are transmitted to the fumigation effect evaluation module as stable and effective monitoring data.

[0028] The anti-interference processing module can adaptively adjust the process noise covariance matrix Q and the observation noise covariance matrix R of the Kalman filter according to the noise characteristics of the collected data. The specific implementation method is as follows: 1. Noise Characteristic Detection: This involves analyzing the residuals (observed values ​​Z) over several consecutive acquisition cycles.k Compared with the predicted value Calculate the variance σ of the difference) 2 and the mean μ of the historical noise variance σ Comparison, if σ 2 >1.5μ σ If so, it is determined that the current noise variance has increased; 2. Matrix element adjustment rules: If the noise is detected to be mainly caused by process interference (such as electromagnetic interference generated by the operation of fumigation equipment leading to unstable state changes), then increase the corresponding diagonal elements of the process noise covariance matrix Q; if the noise is detected to be mainly caused by the observation link (such as the increase of sensor noise itself), then increase the corresponding diagonal elements of the observation noise covariance matrix R.

[0029] The fumigation effectiveness evaluation model in the fumigation effectiveness evaluation module calculates the comprehensive fumigation effectiveness index E using the following formula: 1. The fumigation gas concentration item is: And the maximum value is 1, where: C 实际 The real-time fumigation gas concentration output by the anti-interference processing module; C 标准 : Standard concentration of fumigant for the current fumigation target.

[0030] Physical meaning: It reflects the degree to which the actual fumigation concentration covers the standard concentration. The closer the value is to 1, the more the concentration meets the requirements.

[0031] 2. Temperature item is in: T 实际 The real-time temperature of the fumigation chamber output by the anti-interference processing module; T 基准 The reference temperature required for the fumigation process; T 允许波动 The permissible range of temperature fluctuation; Physical meaning: It reflects the relative degree to which the actual temperature deviates from the reference temperature. The closer the value is to 0, the more stable the temperature is near the reference.

[0032] 3. Humidity item is in: RH 实际 The real-time relative humidity of the fumigation chamber output by the anti-interference processing module; RH 基准 The baseline relative humidity required for the fumigation process; RH 允许波动 The permissible range of humidity fluctuations; Physical meaning: It reflects the relative degree to which the actual humidity deviates from the reference humidity. The closer the value is to 0, the more stable the humidity is near the reference.

[0033] 4. Weighting coefficients ω1, ω2, ω3: The constraint is satisfied: ω1 + ω2 + ω3 = 1; Value selection logic: The importance of concentration, temperature, and humidity is weighted according to the characteristics of the fumigation object and the process requirements.

[0034] The preset compliance range of the fumigation effect evaluation module can adaptively adjust according to the type of fumigation object. The system has a built-in fumigation object database, which contains C corresponding to different objects. 标准 T 基准 T 允许波动 RH 基准 RH 允许波动 The system assigns initial weights ω1, ω2, and ω3. After the user selects the fumigation target through the system interface, the module automatically loads the corresponding parameters and adjusts the target range accordingly.

[0035] The fumigation parameter optimization control model of the intelligent control module is a multi-objective optimization model, with the objective function being: minF=α·E energy -β·(1-R 达标 ); 1. Weighting coefficients α and β, satisfying the constraint: α + β = 1, and both α and β are non-negative numbers, are used to balance the priority of fumigation energy consumption and fumigation effect compliance rate. If energy saving is a greater priority (such as in long-term fumigation scenarios), α = 0.6 and β = 0.4 can be set. If the focus is more on the fumigation effect (such as in emergency pest control scenarios), α = 0.3 and β = 0.7 can be set.

[0036] 2. Fumigation energy consumption E energy This refers to the total energy consumption of all equipment (heaters, humidifiers, fumigation gas generators, fans, etc.) during the fumigation process. Exact calculation (integral form): Where t0 is the start time of fumigation, t1 is the current time, n is the total number of devices participating in fumigation, and P i (t) represents the real-time power of the i-th device at time t; Approximate calculation (average power form): If the equipment power is relatively stable, it can be simplified to: in Let t be the average power of the i-th device within [t0, t1], and Δt = t1 - t0 be the time length.

[0037] 3. Fumigation effect compliance rate R 达标The comprehensive fumigation effect index E refers to the proportion of the total fumigation time within the preset acceptable range, with a value range of [0, 1]. The calculation formula is as follows: Where t 总 t represents the total duration from the start of fumigation to the present. 达标 For t 总 Inside, the comprehensive fumigation effect index E is within the preset acceptable range. To ensure the safety, effectiveness, and operational limitations of fumigation, the model must meet the following constraints: 1. Temperature constraints: The temperature T inside the fumigation chamber must be within the allowable range of the process. min ≤T≤T max T min T is the lower limit of temperature. max This is the upper limit of the temperature range; 2. Humidity constraints: The relative humidity (RH) inside the fumigation chamber must be within the allowable range of the process. min ≤RH≤RH max , of which RH min The lower limit of humidity, RH max This is the upper limit of humidity. 3. Gas concentration constraints: The concentration of fumigation gas C must be within an effective and safe range: C min ≤C≤C max C min C is the lower limit of concentration. max This represents the upper limit of concentration.

[0038] The multi-objective optimization model is solved using an intelligent optimization algorithm to obtain the dynamic adjustment parameters for temperature T, humidity RH, and fumigation gas concentration C. The solution process is as follows: 1. Encoding: Encode the candidate values ​​of temperature T, humidity RH, and concentration C with real numbers (directly using the parameter values ​​as genes) to construct chromosomes; 2. Fitness function: Based on the objective function F = α·E energy -β·R 达标 As a fitness metric (which needs to be minimized F), a constraint violation metric is also introduced: if a parameter violates the temperature, humidity, or concentration constraints, the fitness metric is reduced according to the degree of violation. 3. Genetic manipulation: Selection: A roulette wheel selection method is used, and individuals with higher fitness have a greater probability of being selected; Crossover: A single-point crossover is used to exchange partial genes between two parent chromosomes to generate offspring; Variation: Gaussian variation is used to add random perturbations with a Gaussian distribution to chromosome genes to increase population diversity; 4. Iteration Termination: When the number of iterations reaches a preset value or the population fitness tends to stabilize, the iteration is terminated and the best individual is selected.

[0039] The optimal temperature T, humidity RH, and fumigation gas concentration C for each individual are the dynamic adjustment parameters. The system sends these parameters to the controllers of the actuators (heater, humidifier, and fumigation gas generator) to achieve intelligent adjustment of the fumigation parameters.

[0040] The intelligent control module can dynamically adjust the weight coefficients α and β in the multi-objective optimization model based on the real-time evaluation results of the fumigation effect evaluation module. If the fumigation effect is not up to standard (i.e., E exceeds the preset standard range), then increase the value of β and decrease the value of α, prioritizing ensuring the fumigation effect compliance rate R. 达标 ; If the fumigation effect remains within the acceptable range (e.g., E remains within the acceptable range for 30 consecutive minutes), then increase the value of α and decrease the value of β, prioritizing the reduction of fumigation energy consumption E. energy .

[0041] The remote interaction module includes a data upload unit, a command receiving unit, and a multi-terminal adaptation unit; The data uploading unit uploads the collected data, the data after anti-interference, the fumigation effect evaluation results, and the control parameters to the remote monitoring platform in encrypted form in real time, ensuring the confidentiality and integrity of data transmission. The instruction receiving unit receives control instructions and parameter configuration instructions issued by the remote monitoring platform, and forwards the instructions to the corresponding modules for execution; The multi-terminal adaptation unit supports access to the system via web pages or apps from multiple terminals such as computers, tablets, and mobile phones, enabling: View the real-time changes in temperature, humidity, pressure, and gas concentration. Review the fumigation effect report; Remotely modify fumigation control parameters.

[0042] The system's multi-point acquisition unit, anti-interference processing module, and some intelligent control modules are integrated inside a cabinet with casters, making it easy to move in the field. The cabinet is also equipped with a backup power unit, which can support the system to run continuously for at least 2 hours when the external power supply is interrupted.

[0043] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0044] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A mobile intelligent fumigation anti-interference control system, characterized in that, The system comprises a data acquisition module, an anti-interference processing module, a fumigation effect evaluation module, an intelligent control module and a remote interaction module; The data acquisition module is configured to acquire real-time data of temperature, humidity, pressure and fumigation gas concentration at multiple measuring points in the fumigation warehouse, and transmit the acquired data through a wired or wireless communication interface; The anti-interference processing module is configured to suppress interference signals based on the acquired data by using a fusion filtering algorithm, and output stable effective monitoring data; The fumigation effect evaluation module is configured to construct a fumigation effect evaluation model based on the effective monitoring data, calculate a fumigation effect comprehensive index, and compare the fumigation effect comprehensive index with a preset threshold to determine whether the fumigation is up to standard; The intelligent control module is configured to receive the fumigation effect evaluation result, construct a fumigation parameter optimization control model, and dynamically adjust temperature, humidity and gas concentration parameters in the fumigation process; The remote interaction module is configured to interact the acquired data, anti-interference result, fumigation effect evaluation result and control instruction with a remote monitoring platform, and support multi-terminal access and control.

2. The mobile intelligent fumigation anti-interference control system according to claim 1, characterized in that: The data acquisition module comprises a multi-measuring-point acquisition unit, a communication unit and a synchronization unit; The multi-measuring-point acquisition unit is configured to synchronously acquire temperature, humidity, pressure and fumigation gas concentration data at at least three measuring points in the fumigation warehouse, and the acquisition frequency is configurable; The communication unit supports multiple access modes such as wired, WiFi, 4G or 5G, and transmits the acquired data to the anti-interference processing module in real time; The synchronization unit is configured to synchronize and calibrate the acquisition time of the multiple measuring points, and ensure the time consistency of the multi-source data.

3. The mobile intelligent fumigation anti-interference control system according to claim 1, characterized in that: The anti-interference processing module uses a filtering algorithm that fuses Kalman filtering and wavelet denoising, and the specific processing steps are as follows: Step one: preliminary denoising of the acquired data by wavelet denoising to obtain preliminary denoised data; Step two: further filtering of the preliminary denoised data based on Kalman filtering, State equation is: X k = AX k-1 + BU k + W k ; The observation equation is: Z k = HX k + V k ; wherein X k is the system state at time k, Z k is the observation at time k, A, B, H are state transition, control input, and observation matrices, respectively, W k , V k are process noise and observation noise; Step three: output of the effective monitoring data after fusion filtering.

4. The mobile intelligent fumigation anti-interference control system according to claim 3, characterized in that, The anti-interference processing module can adaptively adjust the process noise covariance matrix Q and the observation noise covariance matrix R of Kalman filtering according to the noise characteristics of the acquired data; The adjustment rule is: when the noise variance is detected to increase, the corresponding element value of Q or R is increased accordingly.

5. The mobile intelligent fumigation anti-interference control system according to claim 1, characterized in that: The fumigation effect evaluation model of the fumigation effect evaluation module is realized by calculating the fumigation effect comprehensive index E, and the calculation formula is: wherein T 实际 , T 基准 , T 允许波动 are actual, reference, allowable fluctuation temperatures, RH 实际 , RH 基准 , RH 允许波动 are actual, reference, allowable fluctuation humidities, the maximum value of which is 1 ; When E is within the preset standard interval, it is determined that the fumigation is up to standard, otherwise it is not up to standard.

6. The mobile intelligent fumigation anti-interference control system according to claim 5, characterized in that: The preset standard interval of the fumigation effect evaluation module can be adaptively adjusted according to the type of the fumigation object; By built-in fumigation object database, when selecting different fumigation objects, automatically match the corresponding C 标准 , T 基准 , RH 基准 parameters, and then adjust the compliance interval.

7. The mobile intelligent fumigation anti-jamming control system of claim 1, wherein: The fumigation parameter optimization control model of the intelligent control module is a multi-objective optimization model, and the objective function is: minF = a · E energy - β · (1 - R 达标 ), Wherein, α+β=1 is a weight coefficient, and α and β are both non-negative numbers, E energy is the fumigation energy consumption, R 达标 is the fumigation effect compliance rate; The constraints include a temperature constraint T min ≤ T ≤ T max , a humidity constraint RH min ≤ RH ≤ RH max , a gas concentration constraint C min ≤ C ≤ C max ; By solving the model, the dynamic adjustment parameters of temperature, humidity and gas concentration are output.

8. The mobile intelligent fumigation anti-interference control system according to claim 7, characterized in that: The intelligent control module can dynamically adjust the weight coefficients α and β in the multi-objective optimization model according to the real-time evaluation result of the fumigation effect evaluation module; When the fumigation effect is not up to standard, the value of β is increased and the value of α is reduced to prioritize ensuring the fumigation effect up to standard rate.

9. The mobile intelligent fumigation anti-jamming control system of claim 1, wherein, The remote interaction module comprises a data uploading unit, an instruction receiving unit and a multi-terminal adaptation unit; The data uploading unit uploads the collected data, the anti-interference data, the fumigation effect evaluation result and the control parameter in encrypted form to a remote supervision platform in real time; The instruction receiving unit receives control instructions and parameter configuration instructions issued by the remote supervision platform; The multi-terminal adaptation unit supports multiple terminals such as computers, tablets and mobile phones to access the system through a webpage or an APP, so as to realize data viewing and remote control.

10. The mobile intelligent fumigation anti-jamming control system of claim 1, wherein: The multi-measurement-point collecting unit, the anti-interference processing module and part of the intelligent control module of the system are integrated in a cabinet with a pulley, which facilitates on-site movement. A backup power supply unit is further arranged in the cabinet, which can support the system to continuously operate for at least 2 hours when external power supply is interrupted.

Images