Environmental adaptation linkage control system and method for outdoor water production equipment

Abstract

The invention discloses an environment adaptation linkage control system and method for outdoor water production equipment, belongs to the technical field of intelligent control, and aims at solving the problems that traditional outdoor water production equipment is poor in environment adaptability, lagged in abnormal response and low in biological invasion prevention and control efficiency. The method comprises the following steps: collecting, classifying and storing environmental parameters of each device in a working area to construct an area data set, obtaining an environmental common mode through time sequence statistical analysis, dividing a control time period and matching typical operation parameters; a differentiated detection period is configured according to the stability of an environment generality mode, environment abnormity is detected in real time, correction is executed, and a control period is optimized through statistical analysis; meanwhile, intrusion data are collected to divide defense time periods, and biological intrusion is monitored in non-defense time periods to dynamically adjust the defense time periods. The environment adaptability and the operation stability of the equipment can be remarkably improved, the prevention and control accuracy of biological invasion is enhanced, and efficient and reliable operation of the outdoor water production equipment is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and more specifically to an environmental adaptation linkage control system and method for outdoor water purification equipment. Background Technology

[0002] Outdoor water production equipment is widely used in remote, water-scarce villages, field exploration camps, natural disaster emergency relief, and water supply scenarios in special climate zones such as islands and plateaus. It is a key piece of equipment for ensuring outdoor water supply. These devices operate in complex outdoor environments for extended periods, where temperature, humidity, dust concentration, sunlight, and wind speed directly affect water production efficiency, operational stability, and component lifespan. They also face risks of component damage and water pollution caused by biological invasions such as rodents and birds. Therefore, they have extremely high requirements for environmental adaptability, anomaly response, and intrusion prevention.

[0003] However, current operation, control, and protection solutions for outdoor water purification equipment still have significant limitations: In terms of environmental adaptability, existing equipment mostly uses fixed operating parameters or relies on manual experience to set control rules, failing to dynamically adjust the operating status according to the periodic changes in the overall working environment. This results in low water production efficiency during certain periods and even increased component wear due to parameter mismatch. In terms of handling environmental anomalies, existing monitoring methods mostly use uniform and fixed detection intervals, which easily lead to missed detections of frequently fluctuating environmental parameters and unnecessary energy waste for stable parameters. Moreover, after anomalies occur, they mostly rely on generalized adjustment schemes, making it difficult to accurately adapt to the local abnormal environment of a single device, further reducing the stability of equipment operation. In the field of biological invasion prevention and control, traditional solutions either adopt a 24-hour continuous operation mode for defense devices, resulting in a significant increase in additional energy consumption, or only activate a passive response after biological invasion of the equipment, which can easily cause component damage or water pollution. Furthermore, they cannot adjust defense strategies according to changes in biological activity patterns in the working area, making it difficult to balance the accuracy of prevention and control with energy efficiency. The aforementioned problems collectively result in poor overall performance of current outdoor water production equipment in complex outdoor environments, failing to fully meet the needs of various outdoor scenarios for stable, efficient, and safe water supply. Therefore, in order to overcome these limitations, this invention proposes an environmental adaptation linkage control system and method for outdoor water production equipment. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide an environmental adaptation linkage control system and method for outdoor water purification equipment. This system solves the problem of how to adapt outdoor water purification equipment to changes in the working environment to achieve precise control and operation, while also timely identifying and handling environmental anomalies and optimizing the operating period. Furthermore, it effectively prevents biological invasion and flexibly adjusts the biological invasion defense period.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] Outdoor water purification equipment environmental adaptation linkage control system, including:

[0007] The data hub module is used to collect and classify environmental parameters and intrusion data of each outdoor water treatment device within the working area, and to construct regional datasets and intrusion datasets respectively.

[0008] The regulation and correction module, based on a regional dataset, performs time-series statistical analysis on environmental parameters in the work area to obtain common environmental patterns, divides control periods, and matches typical operating parameter values ​​for each control period to regulate the operation of outdoor water treatment equipment. Furthermore, based on the stability of the common environmental patterns of each outdoor water treatment device, it configures differentiated detection cycles for each type of environmental parameter. This is used to perform environmental anomaly checks on the outdoor water treatment equipment based on real-time environmental parameters, determining whether any anomalies exist. If anomalies are found, it performs correction operations for the abnormal outdoor water treatment equipment and corrects the control period divisions for the abnormal outdoor water treatment equipment through typical statistical analysis.

[0009] The intrusion prevention module is used to divide intrusion defense periods based on the intrusion dataset, and during non-intrusion defense periods, it determines whether outdoor water treatment equipment has been subjected to biological intrusion, so as to dynamically adjust the division of intrusion defense periods.

[0010] Specifically, the steps to obtain common patterns in the work area environment include:

[0011] Within the work area, environmental parameters of each outdoor water treatment device are collected and categorized by device identifier, collection timestamp, and parameter type, and stored in the regional dataset through a distributed storage architecture.

[0012] The environmental parameters in the regional dataset are preprocessed, including filling in missing values, removing extreme outliers, and standardizing the units, to obtain a standardized regional dataset.

[0013] Time series statistical analysis was performed on the environmental parameters of the regional dataset. The STL time series decomposition method was used to split the trend, periodic and residual terms of the environmental parameters. The periodic fluctuation characteristics of the environmental parameters were identified by periodic spectrum analysis and autocorrelation function test.

[0014] Calculate the correlation coefficients between environmental parameters, and extract the correlation trend characteristics of different environmental parameters by setting a correlation coefficient threshold and testing the consistency with the time series trend.

[0015] Clustering algorithms are used to cluster the combinations of environmental parameters for each time period of the day, and the parameter features of each time period are extracted and clustered.

[0016] Based on the periodic fluctuation patterns, correlation trends, and parameter clustering of environmental parameters, a common environmental pattern for the work area is constructed to divide the control period.

[0017] Specifically, the steps of dividing control periods and matching typical operating parameter values ​​for each control period include:

[0018] The basic time period is divided according to the characteristics of periodic fluctuations;

[0019] The basic time period is subdivided by calculating the similarity of parameter feature clusters, and continuous basic time periods of parameter feature clusters with similarity greater than or equal to a preset similarity threshold are merged into independent control time periods.

[0020] When the cluster similarity of parameter features between basic time periods is less than the preset similarity threshold, if the similarity of the correlation trend features between basic time periods is greater than or equal to the preset similarity threshold, they are merged into independent control time periods.

[0021] Configure the parameter fluctuation thresholds for each environmental parameter, identify abnormal time points where the values ​​of various environmental parameters exceed the corresponding parameter fluctuation thresholds, perform time-series clustering on the abnormal time points, and obtain potential abnormal time periods for various environmental parameters; filter potential abnormal time periods whose duration is greater than a preset basic time length threshold as the abnormal control time periods for the corresponding environmental parameters;

[0022] By combining independent control periods and abnormal control periods, a set of control periods is formed. The environmental parameter feature set of each control period is extracted, and the typical operating parameter values ​​of outdoor water treatment equipment are matched based on the environmental operating parameter mapping set.

[0023] Specifically, the steps for configuring differentiated detection cycles for each type of environmental parameter include:

[0024] Define the assessment period and divide it into multiple assessment sub-periods of equal length, each of which contains a complete set of control periods;

[0025] The environmental parameters of all outdoor water treatment equipment within the evaluation period are retrieved, categorized by evaluation sub-period, control period, and equipment identification, and the common environmental patterns of each control period under each evaluation sub-period are extracted to construct an associated dataset.

[0026] For the environmental parameters of each control period under each evaluation sub-cycle, calculate stability indices, including deviation, fluctuation frequency, and trend fit:

[0027] After standardizing each stability index, the weighted summation method is used to calculate the overall stability score of each type of environmental parameter under the control period of a single assessment sub-cycle, and the average of the overall stability scores of all assessment sub-cycles is taken as the stability score of that type of environmental parameter in the corresponding assessment cycle.

[0028] Based on the stability scores of each environmental parameter in the corresponding evaluation period, the corresponding detection period is matched.

[0029] Specifically, the deviation refers to the average degree of deviation between the actual collected values ​​of environmental parameters and the typical parameter values ​​in the common environmental model during a certain control period within the evaluation sub-cycle.

[0030] Fluctuation frequency refers to the number of times within a certain control period, the actual collected value of environmental parameters exceeds the range of environmental fluctuations under the common environmental pattern of that control period;

[0031] Trend fit refers to the degree of overlap between the actual trend curve of environmental parameters under a certain control period within the evaluation sub-cycle and the periodic fluctuation trend curve in the common environmental pattern of that control period.

[0032] Specifically, the steps for performing environmental anomaly testing on outdoor water treatment equipment and determining whether there are any abnormalities in environmental parameters include:

[0033] Call the environmental parameter constraint range of the current control period of the outdoor water treatment equipment, and at the same time obtain the threshold of the number of deviations of the environmental parameters within the control period;

[0034] According to the configured detection cycle, real-time environmental parameters are obtained. After the real-time environmental parameters are processed by data standardization, they are compared with the environmental parameter constraint range of the current control period parameter by parameter.

[0035] If the real-time value of an environmental parameter is within the corresponding environmental parameter constraint range, the environmental parameter is determined to be normal; otherwise, the environmental parameter is determined to be potentially abnormal and is marked as a potentially abnormal parameter.

[0036] The number of times potential abnormal parameters occur during the current control period is counted. If the number of occurrences exceeds the deviation threshold, the current environmental parameter is determined to be an abnormal environmental parameter; otherwise, it is determined to be a transient fluctuation.

[0037] Specifically, the steps for correcting the control period division of abnormal outdoor water treatment equipment include:

[0038] For each abnormal outdoor water treatment device, the number of times abnormal environmental parameters occur during each control period is counted. If the number exceeds the abnormal warning threshold, the control period correction for the abnormal outdoor water treatment device is triggered.

[0039] Based on the regional dataset, the occurrence time of abnormal environmental parameters of abnormal outdoor water treatment equipment, the deviation between abnormal environmental parameters and the corresponding control period constraint range, and the duration of a single abnormality are extracted to construct a corrected dataset.

[0040] For each abnormal environmental parameter value, compare it with the corresponding parameter fluctuation threshold. If it is greater than the corresponding parameter fluctuation threshold, mark it as an abnormal control period correction; otherwise, mark it as an independent control period correction.

[0041] For abnormal environmental parameters marked as requiring correction during abnormal control periods, a density clustering algorithm is used to perform temporal clustering of their occurrence times to identify continuously occurring stable abnormal periods. The total duration of the stable abnormal periods is calculated. If it exceeds a preset basic time length threshold, it is determined to be a newly added abnormal control period that needs to be supplemented. If the newly added abnormal control period overlaps with the existing abnormal control period, the overlapping abnormal control periods are merged and their environmental parameter constraint ranges are adjusted. Otherwise, environmental parameter constraint ranges and corresponding typical operating parameter values ​​are set separately for them.

[0042] For abnormal environmental parameters marked as being corrected for independent control periods, the original independent control periods to which they belong are extracted. A clustering algorithm is used to combine the occurrence time and deviation of the abnormal environmental parameters within the independent control period, and the original independent control period is subdivided into multiple independent control sub-periods. The environmental parameter constraint range is reset for each independent control sub-period, and typical operating parameter values ​​that are suitable for the characteristics of the sub-period are retrieved from the environmental operating parameter mapping set.

[0043] Specifically, the steps for dividing intrusion prevention time periods include:

[0044] For each intrusion type, the initial time period is divided according to a fixed time granularity. The intrusion frequency of each initial time period is counted. The initial time period with an intrusion frequency greater than a preset frequency threshold is marked as a potential risk period.

[0045] For each type of intrusion, the number of intrusions at different device locations during the potential risk period is counted, the proportion of intrusions at each location to the total number of intrusions during that period is calculated, and the key intrusion areas are located based on the intrusion proportion.

[0046] Density clustering algorithm is used to cluster and merge potential risk periods of the same intrusion type as intrusion defense periods;

[0047] For potential risk periods that are isolated after clustering, if their key intrusion areas coincide with adjacent intrusion defense periods, they are merged into the adjacent intrusion defense periods.

[0048] Specifically, the steps for dynamically adjusting the division of intrusion prevention periods include:

[0049] During non-intrusion defense periods, intrusion data within the work area is continuously collected to construct a non-defense period intrusion dataset and conduct multi-dimensional statistical analysis: for each intrusion type or intrusion device location, the timestamp of each intrusion under that intrusion type or intrusion device location is tracked one by one, and the monitoring period range to which each intrusion timestamp belongs is defined, and the total number of intrusions of that intrusion type or intrusion device location within that monitoring period range is counted.

[0050] If the total number of intrusions of a certain type or the location of the intruding device within a certain monitoring period exceeds a preset frequency threshold, it is marked as a monitoring period to be merged.

[0051] Based on the timestamp of the intrusion that occurred during the monitoring period to be merged, intrusion defense periods with the same intrusion type or intrusion device location as the monitoring period to be merged are selected in the current intrusion defense period. The target intrusion defense period is located by combining the time interval between the monitoring period to be merged and the intrusion defense period, and the start and end times of the target intrusion defense period are updated and adjusted.

[0052] Outdoor water purification equipment environmental adaptation and linkage control methods include:

[0053] Step S1: Collect and classify the environmental parameters and intrusion data of each outdoor water treatment device in the work area, and construct the regional dataset and the intrusion dataset respectively;

[0054] Step S2: Based on the regional dataset, perform time-series statistical analysis on the environmental parameters of the work area, obtain common environmental patterns in the work area, divide the control period, and match the typical operating parameter values ​​for each control period;

[0055] Step S3: Based on the current control period of the outdoor water purification equipment, call typical operating parameter values ​​to regulate the operation of the outdoor water purification equipment, and configure differentiated detection cycles for each type of environmental parameter according to the stability of the common environmental mode of each outdoor water purification equipment.

[0056] Step S4: Based on real-time environmental parameters, perform an environmental anomaly check on the outdoor water production equipment to determine whether there are any anomalies in the environmental parameters. If there are, perform an abnormal outdoor water production equipment correction operation and correct the control period division of the abnormal outdoor water production equipment through typical statistical analysis.

[0057] Step S5: Based on the intrusion dataset, divide the intrusion defense period and determine whether the outdoor water treatment equipment has been invaded by biological forces during the non-intrusion defense period in order to dynamically adjust the division of the intrusion defense period.

[0058] The beneficial effects of this invention are:

[0059] This application effectively solves the problems of poor environmental adaptability, low anomaly response efficiency, high energy consumption, and difficulty in balancing the accuracy and energy efficiency of biological invasion prevention and control in existing outdoor water treatment equipment by collecting and analyzing environmental parameters of outdoor water treatment equipment in the working area, configuring differentiated monitoring and anomaly correction schemes for different environmental parameter characteristics, and dynamically optimizing defense periods by combining biological invasion data. It enables the equipment to dynamically adjust its operating status according to the periodicity and correlation characteristics of the regional environment, improving water treatment efficiency and reducing wear and tear on core components. In handling environmental anomalies, it ensures timely identification of anomalies through differentiated monitoring, avoids redundant monitoring of stable parameters to reduce energy consumption, and adapts to local anomalies in individual equipment through precise correction schemes, further improving operational stability. In terms of biological invasion prevention and control, it can flexibly adjust defense periods according to biological activity patterns, reducing the additional energy consumption of continuous defense and lowering the risk of equipment damage and water pollution caused by passive response. Ultimately, it significantly improves the overall operating performance of outdoor water treatment equipment in complex outdoor environments, fully meeting the needs of various outdoor scenarios for stable, efficient, and safe water supply. Attached Figure Description

[0060] Figure 1 This is a schematic diagram of the environmental adaptation linkage control system for the outdoor water purification equipment of the present invention.

[0061] Figure 2 This is a flowchart illustrating the division of control time periods in this invention;

[0062] Figure 3 This is a flowchart illustrating the process of configuring differentiated detection cycles for each type of environmental parameter according to the present invention;

[0063] Figure 4 This is a flowchart illustrating the control time period division of the abnormal outdoor water production equipment of the present invention;

[0064] Figure 5 This is a flowchart of the environmental adaptation and linkage control method for outdoor water treatment equipment according to the present invention. Detailed Implementation

[0065] Please see Figure 1 This embodiment introduces an environmental adaptation and linkage control system for outdoor water treatment equipment, including a data hub module, a regulation and correction module, and an intrusion prevention and control module.

[0066] The data hub module deploys multi-dimensional environmental monitoring points for each outdoor water treatment device within the working area, synchronously collecting various environmental parameters affecting the operation of the outdoor water treatment devices. It also adopts a distributed storage architecture to classify and store the environmental parameters of each outdoor water treatment device within the working area, constructing a regional dataset. Infrared monitoring devices and vibration sensors are deployed at key protection locations of each outdoor water treatment device to collect intrusion data of each outdoor water treatment device within the working area, constructing an intrusion dataset to provide benchmark parameters for the coordinated control of outdoor water treatment devices.

[0067] In this embodiment, the working area refers to a specific outdoor space where outdoor water production equipment is centrally deployed and requires unified environmental adaptation and control. This includes, but is not limited to, the following scenarios: centralized water supply areas in villages or communities in remote, water-scarce areas; water supply areas for temporary camps during field exploration or engineering operations; emergency water supply and rescue areas after natural disasters; and the coverage area of ​​fixed water supply stations in special climate zones such as islands or plateaus. Environmental parameters refer to outdoor environmental characteristics that directly or indirectly affect the water production efficiency, operational stability, and component lifespan of outdoor water production equipment, including temperature and humidity parameters, dust concentration parameters, light intensity parameters, and wind speed parameters. Critical protection locations refer to outdoor water production equipment that is susceptible to biological invasion, and where such invasion would directly affect the operation of the equipment or the safety of the water quality. The core components include the outer side of the equipment's air inlet filter, the area around the water tank inspection port, the outer shell of the circuit compartment, and the top and bottom supports of the equipment. The infrared monitoring device and vibration sensor are combined monitoring components that work together to collect intrusion signals. The infrared monitoring device identifies the approach of a living organism by detecting the infrared radiation emitted from its surface, and can distinguish the size of the organism to make a preliminary judgment on the type of intrusion. The vibration sensor supplements the identification of static or low-temperature organisms by sensing the vibration generated when a organism comes into contact with the equipment. The fusion of the two data improves the accuracy of intrusion identification. Intrusion data refers to the full-dimensional information related to biological intrusion collected by the monitoring components, including the timestamp of the intrusion, the location of the equipment that triggered the intrusion, the heat source intensity of the infrared signal, and the frequency and amplitude of the vibration signal.

[0068] Because traditional outdoor water treatment equipment often limits environmental data collection to local points of a single device, it is difficult to cover the overall environmental characteristics of the work area. Furthermore, the collection of intrusion data lacks a unified deployment and standardized processing mechanism. Environmental data and intrusion data are stored in a scattered manner and lack correlation analysis, resulting in the inability to effectively identify common patterns in the regional environment and biological invasion characteristics. The data hub module deploys multi-dimensional environmental monitoring points for each outdoor water treatment device in the work area, and deploys infrared monitoring devices and vibration sensors at key protection locations to achieve synchronous collection of environmental parameters and intrusion data. Combined with a distributed storage architecture, environmental parameters and intrusion datasets are stored in categories to construct a regional dataset containing both types of data. This solves the problems of fragmented data and insufficient standardization of intrusion data, providing a comprehensive structured data foundation for subsequent integrated analysis.

[0069] The regulation and correction module, based on a regional dataset, performs time-series statistical analysis of environmental parameters in the work area to obtain common environmental patterns, divides control periods, and matches typical operating parameter values ​​for each control period. It then regulates the operation of outdoor water treatment equipment and, based on the stability of the common environmental patterns of each outdoor water treatment device, configures differentiated detection cycles for each type of environmental parameter. This is used to perform environmental anomaly checks on the outdoor water treatment equipment based on real-time environmental parameters, determining whether any environmental parameters are abnormal, i.e., whether the current environmental parameter values ​​of the outdoor water treatment equipment conform to the environmental parameter constraints of the current control period. If not, it performs an abnormal outdoor water treatment equipment correction operation, dynamically adjusting the typical operating parameter values ​​of the current control period. It also performs typical statistical analysis on the occurrence time of abnormal environmental parameters of the abnormal outdoor water treatment equipment and their relative deviation from the environmental parameter constraints. This analysis is used to correct the current control period division of the outdoor water treatment equipment and update the matched typical operating parameter values.

[0070] In this embodiment, the common environmental pattern refers to the regular variation characteristics of environmental parameters in the working area over time, which are common to outdoor water purification equipment. Specifically, this includes the periodic fluctuation pattern of environmental parameters, the correlation trend between different environmental parameters, and parameter feature clustering for specific time periods. Typical operating parameter values ​​refer to the reference operating parameters that enable outdoor water purification equipment to achieve efficient water production, stable operation, and adapt to the current environmental characteristics during each control period divided by the control and correction module, based on the common environmental pattern of the working area and the regional dataset analysis. Specifically, these parameters include the operating parameters of core components, energy consumption allocation parameters, and water production performance target parameters. The stability of the common environmental pattern refers to the degree of fluctuation and regularity of environmental parameters within the working area during the corresponding control period. Specifically, it is manifested in the deviation range, frequency, and duration of the actual environmental parameter values ​​from the typical parameter values ​​of that period. If the deviation is small, the frequency is low, and the duration is short, the stability is high; conversely, the stability is low. Differentiated detection cycle refers to the different detection intervals set for each type of environmental parameter based on the stability of the common environmental pattern. Longer detection cycles are set for environmental parameters with high stability, and shorter detection cycles are set for environmental parameters with low stability, in order to reduce unnecessary energy consumption while ensuring the anomaly detection rate. Environmental anomaly inspection refers to comparing the environmental parameters collected in real time by the outdoor water purification equipment with the environmental parameter constraint range preset by the control and correction module for the current control period to identify environmental anomalies, including sudden sandstorms, sudden increases in local temperature, etc. Single equipment operation correction operation refers to the operational parameter adjustment measures performed on a single outdoor water purification equipment when the environmental anomaly inspection determines that it is abnormal. Specifically, this includes adjusting the compressor power to adapt to sudden temperature changes, increasing the filter backflushing frequency to cope with sudden sandstorms, and increasing the fan speed to alleviate local heat accumulation, etc., aiming to adapt the equipment to the current abnormal environment.

[0071] Traditional outdoor water purification equipment often employs a one-size-fits-all approach in its control, ignoring the differences between the local environment of a single unit and the overall regional environment, and lacking a dynamic response mechanism for environmental anomalies. This results in low operating efficiency and poor stability of the equipment under localized abnormal conditions. The control and correction module first performs time-series statistical analysis of environmental parameters in the working area based on a regional dataset to obtain common environmental patterns. It then divides control periods and matches typical operating parameter values, including core component operating parameters, energy consumption allocation parameters, and water purification performance target parameters, to regulate the operation of the outdoor water purification equipment. Furthermore, by configuring differentiated detection cycles based on the stability of common environmental patterns, it ensures high-frequency monitoring of highly fluctuating environmental parameters for rapid identification. This approach avoids anomalies and redundant detection of stable parameters, thus reducing energy consumption. By linking environmental anomaly detection with single-device operation correction, the equipment can adapt to local anomaly environments in real time, solving the problem that regional common control cannot cover the special needs of individual devices. Through typical statistical analysis of correction operations, local anomaly patterns are fed back to the data hub module to correct the control period division and update typical operating parameter values. Ultimately, this achieves an upgrade from regional common benchmark control to dynamic adaptive control combining common and individual characteristics. This not only improves the adaptability of a single outdoor water treatment device to complex local environments but also enhances the self-optimization capability of the control strategy, further ensuring the efficient and stable operation of the equipment in variable outdoor environments.

[0072] Please see Figure 2 Preferably, the specific steps for dividing the control period and matching the typical operating parameter values ​​for each control period include:

[0073] The environmental parameters affecting the operation of outdoor water purification equipment are acquired, including temperature and humidity parameters, dust concentration parameters, light intensity parameters, and wind speed parameters. The environmental parameters of each outdoor water purification device are classified according to equipment identification, collection timestamp, and parameter type, and stored in the regional dataset through a distributed storage architecture to ensure that the data dimensions meet the needs of subsequent pattern analysis.

[0074] The environmental parameters in the regional dataset are preprocessed, including using linear interpolation to fill in missing values ​​caused by temporary equipment failures, and using the 3σ principle to remove extreme outliers, such as false alarms of high temperatures from equipment. Environmental parameters of different dimensions are standardized, such as converting temperature to a standardized value in the [0,1] interval and converting dust concentration to a grade value according to industry standards, to eliminate the influence of differences in the dimensions of parameters on the analysis results, resulting in a clean and uniform standardized regional dataset.

[0075] Time-series statistical analysis was performed on environmental parameters of a standardized regional dataset. The STL time series decomposition method was used to decompose the environmental parameters into trend terms, periodic terms, and residual terms. Periodicity spectrum analysis and autocorrelation function test were used to identify the periodic fluctuation characteristics of the environmental parameters. For example, Fourier transform was performed on the decomposed periodic terms to obtain the periodicity spectrum. The period corresponding to the peak value of the power spectrum was extracted. Combined with the significant peak value of the autocorrelation function when the lag value is an integer multiple of the period, the periodic fluctuation characteristics of temperature and humidity 24-hour diurnal cycle and dust concentration quarterly fluctuation cycle were confirmed.

[0076] The correlation coefficients between environmental parameters are calculated, and the correlation trend characteristics of different environmental parameters are extracted by setting a correlation coefficient threshold and checking the consistency of the time series trend. For example, the negative correlation between rising temperature and decreasing relative humidity, and the positive correlation between increased light intensity and slightly increased wind speed. For example, for parameter pairs whose absolute values ​​of correlation coefficients exceed the correlation coefficient threshold, a sliding window trend curve is plotted, and the stability of the correlation trend is verified by the consistency of the trend slope sign, and the continuous and stable correlation trend characteristics are screened out.

[0077] Clustering algorithms are used to cluster the environmental parameter combinations of each time period of the day, and the parameter features of each time period are extracted and clustered, such as the high humidity, low light and low wind speed features from 6:00 to 9:00 in the morning, and the high temperature, low humidity and high light features from 12:00 to 15:00 in the afternoon.

[0078] Based on the periodic fluctuation patterns, correlation trends, and parameter feature clustering of environmental parameters, a common environmental pattern for the work area is constructed to divide the control period:

[0079] The basic time periods are divided according to the characteristics of periodic fluctuations, such as dividing the 24-hour day-night cycle into daytime and nighttime periods;

[0080] The basic time period is subdivided by calculating the similarity of parameter feature clusters. Continuous basic time periods with parameter feature clusters whose similarity is greater than or equal to a preset similarity threshold are merged into independent control time periods. For example, daytime time periods are subdivided into morning high humidity periods, afternoon high temperature periods, and evening transition periods. The similarity threshold is a critical value used to determine whether the parameter feature clusters or related change trends of continuous basic time periods are consistent and whether they can be merged into independent control time periods. The threshold is set by calculating the initial value using historical data and then verifying and optimizing it through pilot tests.

[0081] When the cluster similarity of parameter features between basic time periods is less than the preset similarity threshold, if the similarity of the correlation trend features between basic time periods is greater than or equal to the preset similarity threshold, they will still be merged into independent control time periods.

[0082] Based on historical data quantiles and equipment tolerance limits, parameter fluctuation thresholds for various environmental parameters are configured. Abnormal time points where the values ​​of various environmental parameters exceed the corresponding parameter fluctuation thresholds are identified. These abnormal time points are then subjected to temporal clustering to obtain potential abnormal periods for various environmental parameters. Potential abnormal periods with durations exceeding a preset base time length threshold are selected as abnormal control periods for the corresponding environmental parameters to supplement special control periods. For example, if the dust concentration is consistently more than twice the normal average, this period is designated as a special dust defense period. The base time length threshold is the minimum duration for screening potential abnormal periods to determine if they are regulatory. It is set as follows: First, the parameter adjustment cycle of the outdoor water treatment equipment is matched, i.e., the shortest time required for the equipment to complete one adjustment of operating parameters. Second, historical abnormal data is analyzed to extract the minimum duration of abnormal periods that can have a real impact on the equipment's operating efficiency and stability. Finally, the larger value between the equipment adjustment cycle and the minimum duration of historical effective abnormal periods is taken as the base time length threshold.

[0083] By combining independent control periods and abnormal control periods, a set of control periods is formed. The environmental parameter feature set of each control period is extracted. Based on the environmental operation parameter mapping set, the typical operation parameter values ​​of the outdoor water production equipment are matched, and the operation parameters of the core components are set. For example, during the morning high humidity period, the compressor cooling power is reduced to 70% of the normal value, and during the special sandstorm defense period, the fan speed is increased to 120% of the normal value. The energy supply type of the equipment is referenced, such as solar power supply, and the energy consumption allocation parameters are matched. For example, during the afternoon high temperature and high sunshine period, the proportion of solar power supply is set to ≥80%, and during the night period, the proportion of energy storage battery power supply is set to 100%. The water production performance target parameters are set by combining the regional water demand and the water production capacity of the equipment. For example, the water production rate is ≥5L / h during the morning high humidity period and ≥3L / h during the night period, forming the typical operation parameter values ​​for each control period. An environmental operation parameter mapping set refers to a pre-constructed set of correspondences between environmental parameter feature sets and typical operating parameter values ​​of equipment, based on historical environmental data of the working area, outdoor water treatment equipment operation test data, and equipment component adaptation characteristics. Its core is to establish clear correspondence rules between environmental characteristics during a specific control period and operating parameter benchmarks that enable equipment to adapt to that environment. This ensures that the corresponding equipment operating parameters can be quickly matched and invoked based on real-time environmental characteristics, providing a standardized basis for setting typical operating parameter values. The environmental operation parameter mapping set contains three core mapping subsets: the first subset is a mapping subset between environmental parameter features and core component operating parameters, used to associate environmental parameter features during the control period with the operating parameters of the equipment's core working components; the second subset is a mapping subset between environmental parameter features and energy consumption allocation parameters, used to associate environmental parameter features during the control period with the energy supply allocation ratio of the equipment; and the third subset is a mapping subset between environmental parameter features and water treatment performance target parameters, used to associate environmental parameter features during the control period with the target value of the equipment's water treatment performance.

[0084] Please see Figure 3 Preferably, the specific steps for configuring differentiated detection cycles for each type of environmental parameter include:

[0085] Based on the short-term fluctuation patterns of environmental parameters in the work area and the continuous operation characteristics of outdoor water treatment equipment, an assessment period covering the stability trend and short-term changes of the environment is defined to ensure that the fluctuation characteristics of environmental parameters in different control periods can be fully captured. The assessment period is further divided into multiple assessment sub-periods of equal length, each containing a complete set of control periods. Through comparative analysis of data from multiple sub-periods, the interference of accidental environmental fluctuations on stability judgment is eliminated, providing a representative data foundation for subsequent extraction of common environmental patterns and stability assessment.

[0086] The system retrieves all environmental parameters for each type of outdoor water treatment equipment within the assessment period, categorizing them by assessment sub-cycle, control period, and equipment identification to ensure accurate correlation between data and time period / equipment. Simultaneously, it extracts common environmental patterns for each control period under each assessment sub-cycle, including the periodic fluctuation characteristics of environmental parameters, the correlation trends between different parameters, and parameter feature clustering for each control period, constructing a correlated dataset to provide a basis for stability quantitative analysis.

[0087] For the environmental parameters of each control period under each evaluation sub-cycle, calculate stability indices, including deviation, fluctuation frequency, and trend fit:

[0088] Deviation refers to the average degree of deviation between the actual collected values ​​of environmental parameters and the typical parameter values ​​in the common environmental pattern of the control period within the evaluation sub-cycle. The typical parameter values ​​refer to the benchmark values ​​that can represent the core characteristics of the parameters in the common environmental pattern of the control period, which are specifically derived from the cluster center values ​​of parameter feature clustering.

[0089] Fluctuation frequency refers to the number of times within a certain control period during an evaluation sub-cycle, the actual collected value of an environmental parameter exceeds the environmental fluctuation range under the common environmental mode of that control period. The environmental fluctuation range refers to the range within which the actual value of the parameter is allowed to fluctuate under normal operating conditions, based on the common environmental mode of that control period.

[0090] Trend fit refers to the degree of overlap between the actual trend curve of environmental parameters under a certain control period within the evaluation sub-cycle and the periodic fluctuation trend curve in the common environmental pattern of that control period.

[0091] For example, regarding the deviation, the cluster center value of the parameter feature cluster for the control period is extracted from the associated dataset as the typical parameter value. Then, the actual parameter values ​​of all devices under the control period within the evaluation sub-cycle are obtained. The absolute deviation between each actual value and the typical parameter value is calculated. The arithmetic mean of all absolute deviations is taken to obtain the deviation of the environmental parameter under the evaluation sub-cycle and control period. Regarding the fluctuation frequency, based on the common environmental pattern of the control period, the environmental fluctuation range is set based on the discrete range of the parameter feature cluster and the fluctuation amplitude of the periodic fluctuation pattern. The total number of times the actual parameter value under the control period exceeds the range within the evaluation sub-cycle is counted. Combined with the duration of the control period, the number of fluctuations per unit time is calculated to obtain the fluctuation frequency. Regarding the trend fit, the periodic fluctuation trend curve in the common environmental pattern of the control period is extracted. The actual collected parameter values ​​are plotted in chronological order as the actual change trend curve. The similarity between the two curves is calculated using the dynamic time warping algorithm. The similarity is normalized to the [0,1] interval to obtain the trend fit.

[0092] After standardizing each stability index, a weighted summation method is used to calculate the stability score of each type of environmental parameter within a single assessment sub-cycle. For example, deviation has the highest weight, following the rule that smaller deviation results in a higher score; fluctuation frequency and trend conformity have the next highest weights, with the former following the rule that fewer fluctuation frequencies result in a higher score, and the latter following the rule that higher conformity results in a higher score. The average of the comprehensive stability scores across all assessment sub-cycles is taken as the final stability score for that type of environmental parameter in the corresponding assessment cycle. Based on the final stability score, the parameters are classified into stability levels: high stability, medium stability, and low stability. High stability corresponds to the highest score range, representing parameters that consistently follow common patterns with minimal fluctuations; medium stability corresponds to the middle score range, representing parameters that occasionally fluctuate but whose overall pattern is controllable; low stability corresponds to the lowest score range, representing parameters that easily deviate from common patterns and fluctuate frequently.

[0093] For environmental parameters with different stability levels, a corresponding initial detection cycle benchmark is matched: high stability level parameters are matched with a longer initial cycle, the purpose of which is to reduce invalid data collection and reduce energy consumption; medium stability level parameters are matched with a medium initial cycle, the core of which is to balance monitoring accuracy and energy consumption cost; low stability level parameters are matched with a shorter initial cycle to ensure that abnormal changes in parameters can be captured in a timely manner.

[0094] Specifically, the steps for performing environmental anomaly testing on outdoor water treatment equipment and determining whether there are any abnormalities in environmental parameters include:

[0095] The system retrieves the environmental parameter constraint range for the current control period of the outdoor water treatment equipment. This constraint range is based on a common environmental model and is a combination of typical parameter values ​​and allowable fluctuation ranges. Simultaneously, it obtains the maximum permissible deviation threshold for environmental parameters within this control period, providing a standard basis for anomaly detection. The deviation threshold refers to the maximum number of consecutive times the actual value of the environmental parameter is allowed to exceed the preset environmental parameter constraint range within the current control period. This threshold is set by combining a base value based on the stability level of the common environmental model, adjusting the response cycle of the core components of the outdoor water treatment equipment, and then optimizing through pilot verification based on historical operating data.

[0096] Based on the differentiated detection cycle configured in the control and correction module, real-time environmental parameters are acquired through multi-dimensional environmental monitoring points deployed in the equipment. The real-time environmental parameters undergo data standardization processing, including noise filtering and the use of a moving average method to eliminate parameter jumps caused by transient interference. For invalid values ​​generated due to temporary equipment malfunctions, linear interpolation is used to supplement valid data, ensuring that the real-time parameters accurately reflect the current environmental state.

[0097] The standardized real-time environmental parameters are compared parameter by parameter with the environmental parameter constraints for the current control period. If the real-time value of an environmental parameter is within the corresponding constraint range, it is determined that the environmental parameter is normal; if the real-time value exceeds the constraint range, it is determined that the environmental parameter has a potential anomaly and is marked as a potential anomaly parameter. The occurrence frequency of potential anomaly parameters in the current control period is counted. If it exceeds the deviation frequency threshold, the current environmental parameter is determined to be an abnormal environmental parameter; otherwise, it is determined to be a transient fluctuation and not considered an environmental anomaly. For abnormal environmental parameters, the correlation between common environmental patterns and historical anomaly records is analyzed to determine the relationship between abnormal environmental parameters and other environmental parameters, accurately identifying the anomaly type. This provides a clear basis for subsequent single-device operation correction operations; if no anomaly is determined, the next inspection is performed according to the differentiated detection cycle.

[0098] For outdoor water purification equipment with abnormal environmental parameters, perform correction operations: Obtain the abnormal environmental parameters involved in the current outdoor water purification equipment, retrieve the correction parameter benchmark that matches the abnormal environmental parameters from the environmental operation parameter mapping set, and adjust the correction parameter range based on the equipment's historical correction records and service life to form a personalized correction plan; send correction instructions, collect the operating data of the core components of the equipment in real time after correction, and determine whether the corrected parameters have fallen back to the normal range and whether the water production efficiency has recovered to the target value; if the correction effect is satisfactory, record the time, correction parameters, and effect of this correction in the correction operation database; if the effect is not satisfactory, fine-tune the correction range based on real-time monitoring data, and repeat the correction and monitoring steps until the equipment adapts to the current abnormal environment.

[0099] Please see Figure 4 Preferably, the specific steps for dividing the control period of abnormal outdoor water treatment equipment include:

[0100] For each abnormal outdoor water treatment device, the number of times abnormal environmental parameters occur during each control period is counted. If the number exceeds the abnormal warning threshold, the control period correction for the abnormal outdoor water treatment device is triggered.

[0101] Based on a standardized regional dataset, the occurrence time of abnormal environmental parameters of abnormal outdoor water treatment equipment, the deviation between abnormal environmental parameters and the corresponding control period constraint range, and the duration of a single abnormality are extracted to construct a corrected dataset, providing data support for identifying stable abnormal periods.

[0102] For each abnormal environmental parameter value, compare it with the corresponding parameter fluctuation threshold. If it is greater than the corresponding parameter fluctuation threshold, it means that the abnormality is a serious abnormality that exceeds the normal fluctuation. It is necessary to add abnormal control periods and mark it as an abnormal control period correction. If the abnormal parameter value is less than or equal to the corresponding parameter fluctuation threshold, it means that the abnormality is a local deviation within the normal fluctuation. It is necessary to optimize the subdivision of the existing independent control periods and mark it as an independent control period correction.

[0103] For abnormal environmental parameters marked as abnormal control periods for correction, density clustering algorithm is used to perform temporal clustering of their occurrence time points, setting time neighborhood and minimum number of cluster points to identify continuously occurring stable abnormal periods.

[0104] Calculate the total duration of stable abnormal periods. If the total duration exceeds the preset basic time length threshold, it is determined to be a new abnormal control period that needs to be added.

[0105] If the newly added abnormal control period overlaps with the existing abnormal control period, the overlapping abnormal control periods will be merged and their environmental parameter constraint ranges will be adjusted; otherwise, environmental parameter constraint ranges and corresponding typical operating parameter values ​​will be set separately for them.

[0106] For abnormal environmental parameters marked as being corrected during independent control periods, their original independent control periods are extracted. A clustering algorithm is then used to combine the occurrence time and deviation of the abnormal environmental parameters within the independent control period, subdividing the original independent control period into multiple independent control sub-periods. For example, if the original morning high humidity period is from 6:00 to 9:00, and there are no abnormalities from 6:00 to 7:30, but frequent small temperature deviations occur from 7:30 to 8:30, then it is divided into the morning high humidity to no deviation sub-period from 6:00 to 7:30 and the morning high humidity to small temperature deviation sub-period from 7:30 to 8:30.

[0107] For each independent control sub-period, the environmental parameter constraint range is reset, and typical operating parameter values ​​that are suitable for the characteristics of the sub-period are retrieved from the environmental operating parameter mapping set to ensure that the sub-period parameters match the local fluctuation characteristics.

[0108] The intrusion prevention module collects intrusion data from each outdoor water treatment device in the work area through the data hub module, constructing an intrusion dataset. By statistically analyzing typical time periods, typical intrusion areas, and intrusion types within the work area, it divides the work area into intrusion defense periods and matches corresponding intrusion defense execution parameter values ​​to each defense period. During the intrusion defense period, corresponding defense measures are activated in advance to form a preventive protective barrier. During non-intrusion defense periods, intrusion data is continuously collected to determine in real time whether the outdoor water treatment devices have encountered biological intrusion. If so, emergency defense measures are immediately activated. At the same time, the frequency and time distribution of intrusion data during non-intrusion defense periods are analyzed to dynamically adjust the division of intrusion defense periods and update the matched intrusion defense execution parameter values, ensuring the adaptability and accuracy of the defense strategy.

[0109] In this embodiment, typical time period, typical invasion area, and invasion type refer to the core characteristics of biological invasion derived through statistical analysis. Typical time period refers to a time period with a significantly higher invasion frequency than other time periods, such as the foraging period for rodents from 18:00 to 20:00 in the evening or the active period for birds from 6:00 to 8:00 in the morning. Typical invasion area refers to specific areas within the work area with a high frequency of equipment invasion, such as edge equipment near weeds or corner equipment away from human activity. Invasion type refers to categories classified according to the mode and size of biological hazard, such as rodents gnawing on parts, birds building nests and blocking access, reptiles entangled in wiring or contaminating water tanks. Invasion defense execution parameter values ​​refer to the values ​​matched for each invasion defense time period and adapted to the corresponding invasion. The technical parameters of the defense measures include the warning frequency and volume level of the audible and visual warning device, the frequency of the ultrasonic repelling device, and the deployment timing and coverage of the physical interception network. Emergency defense measures refer to the rapid response measures that are immediately activated when biological intrusion is detected during non-intrusion defense periods, including instantaneous strong light, high-decibel alarm repelling, maximum power operation of ultrasonic devices, and emergency closure of the physical interception network, while recording intrusion process data for subsequent analysis. Frequency and time period distribution analysis refers to the summary and statistics of intrusion data during non-intrusion defense periods, including the specific time point distribution of intrusions, the proportion of intrusion frequency in different time periods, the correlation between intrusion type and time period, and the identification of whether new intrusion patterns have formed through trend fitting.

[0110] Traditional outdoor water treatment equipment often employs 24-hour continuous defense or a single passive response mode for biological intrusion prevention, which presents two major problems: First, energy waste, as continuously operating defense devices increases equipment energy consumption, especially during periods without intrusion risk; second, delayed and ineffective defense, only initiating a response after biological invasion, which can easily damage components or pollute water, and fails to adjust measures according to the time, area, and type of intrusion. The intrusion prevention module, based on statistical analysis of biological intrusion patterns in the work area, constructs and switches to a proactive defense mode, activating defenses tailored to the intrusion characteristics of the designated intrusion defense period in advance. These measures significantly reduce the probability of successful intrusion, while maintaining low-power monitoring during non-defense periods to reduce unnecessary energy consumption; multi-component fusion monitoring improves the accuracy of intrusion identification and avoids misjudgment by a single sensor; through emergency response and data feedback mechanisms, sudden intrusions are handled quickly, and intrusion data statistics during non-defense periods are used to dynamically optimize the division of defense periods and defense execution parameters, ultimately achieving a shift from passive response to proactive prevention and precise response. This reduces the probability of equipment failure due to biological intrusion, reduces unnecessary energy consumption of defense devices, and improves the adaptability of defense strategies to changes in biological activity patterns in the working area, ensuring the long-term stable operation of outdoor water treatment equipment.

[0111] Preferably, the specific steps for dividing intrusion defense time periods include:

[0112] Intrusion data for each outdoor water treatment device within the work area was acquired, including the intrusion timestamp and the location of the intruding device, such as the outside of the air inlet filter, the water tank inspection port, the intensity of the infrared heat source, and the frequency and amplitude of the vibration signal. Preprocessing was performed, using the 3σ principle to eliminate false alarms caused by environmental interference. Biological size ranges were defined based on the intensity of the infrared heat source, and intrusion types were further subdivided based on vibration signal characteristics. The intrusion data was then categorized and organized according to the intrusion timestamp, intrusion type, and location of the intruding device to construct an intrusion dataset, providing a clean data foundation for subsequent time-series pattern analysis.

[0113] Time-series statistical analysis of the intrusion dataset:

[0114] For each intrusion type, the initial time period is divided according to a fixed time granularity. The intrusion frequency of each initial time period is counted. The initial time period with an intrusion frequency greater than a preset frequency threshold is marked as a potential risk period.

[0115] For each type of intrusion, the number of intrusions at different device locations during the potential risk period is counted, and the proportion of intrusions at each location to the total number of intrusions during that period is calculated. Based on the intrusion proportion, key intrusion areas are located. For example, during the potential risk period for rodents in the evening, the proportion of intrusions outside the air intake filter is high. A correlation table of intrusion type, potential risk period, and key intrusion area is constructed to exclude scattered potential risk periods without high-frequency intrusion areas, ensuring that subsequent defense measures can accurately cover high-risk locations.

[0116] Density clustering algorithm is used to cluster potential risk periods of the same intrusion type. The time neighborhood and the number of clusters are set as clustering parameters. Potential risk periods are merged by clustering and used as intrusion defense periods. For potential risk periods that are isolated after clustering, if their key intrusion area is consistent with the adjacent intrusion defense period, they are merged into the adjacent intrusion defense period; otherwise, they are temporarily classified as periods to be observed.

[0117] Summarize the intrusion prevention time periods for all intrusion types, determine if there are overlapping time periods, initiate scenario-specific adaptation and integration operations, and match the corresponding intrusion prevention execution parameter values;

[0118] If the key intrusion areas for different intrusion types are different during the overlapping period, such as bird intrusions concentrated at the water tank inspection port and rodents concentrated on the outside of the air intake filter, then a zoned defense strategy is adopted. During the overlapping period, corresponding defense measures are activated for different key intrusion areas, such as activating sound and light bird deterrence at the water tank inspection port and activating ultrasonic rodent deterrence on the outside of the air intake filter.

[0119] If the key intrusion areas are the same and the defense measures are compatible within the overlapping time period, the overlapping time period will be merged into a comprehensive defense time period, and the defense parameters covering multiple intrusion types will be uniformly matched, such as adjusting the ultrasonic frequency to the sensitive frequency band that is suitable for the two types of organisms.

[0120] If there are conflicts in defense measures during overlapping periods, such as sound and light warnings being effective for birds but potentially attracting rodents, priority should be given to retaining defense requirements for the more dangerous type of intrusion, such as reptiles easily contaminating water tanks and posing a greater threat than rodents gnawing on the filter screen. The defense period for the other type of intrusion should be adjusted to an adjacent, non-conflicting period, or its defense measures should be optimized, such as changing rodent defenses to physical interception nets to avoid conflict with sound and light warnings.

[0121] Preferably, the steps for dynamically adjusting the division of intrusion prevention time periods include:

[0122] During non-intrusion defense periods, intrusion data within the work area is continuously collected to construct a non-defense period intrusion dataset and conduct multi-dimensional statistical analysis: for each intrusion type or intrusion device location, the timestamp of each intrusion under that intrusion type or intrusion device location is tracked one by one, and the monitoring period range to which each intrusion timestamp belongs is defined, and then the total number of intrusions of that intrusion type or intrusion device location within that monitoring period range is counted.

[0123] If the total number of intrusions of a certain type within a certain monitoring period exceeds a preset frequency threshold, or the total number of intrusions of a certain intrusion device location within a certain monitoring period exceeds a preset frequency threshold, then this monitoring period is used as the core criterion and marked as a monitoring period to be merged. Further, based on the timestamps of intrusion events within this monitoring period to be merged, existing defense periods with the same intrusion type or intrusion device location as the current divided intrusion defense periods are selected as candidate merged defense periods. The time interval between the monitoring period to be merged and each candidate merged defense period is calculated, and the candidate merged defense period with the smallest time interval is preferentially selected as the target intrusion defense period. If multiple candidate merged defense periods have the same and smallest time interval, then the period with the better defense effect is selected as the target period, taking into account the historical defense effect of the candidate periods.

[0124] After determining the target intrusion defense period, the start and end times of the target intrusion defense period are updated and adjusted based on the time range of the monitoring period to be merged: If the monitoring period to be merged is before the start time of the target intrusion defense period and the time interval between the two is small, the start time of the target intrusion defense period is advanced to the start time of the monitoring period to be merged; if the monitoring period to be merged is after the end time of the target intrusion defense period and the time interval between the two is small, the end time of the target intrusion defense period is postponed to the end time of the monitoring period to be merged; if there is some overlap between the monitoring period to be merged and the target intrusion defense period, the two time periods are directly merged to form a new target intrusion defense period covering the complete range; at the same time, it is checked whether the original intrusion defense execution parameters of the target intrusion defense period are suitable for the characteristics of the merged period. If the intrusion intensity of the monitoring period to be merged differs from that of the original target period, the parameters are fine-tuned based on the intrusion data of the monitoring period to be merged to ensure that the merged defense period can accurately respond to intrusion risks.

[0125] Please see Figure 5 This embodiment introduces an environmental adaptation and linkage control method for outdoor water purification equipment, including:

[0126] Step S1: Within the working area of ​​the outdoor water treatment equipment, deploy multi-dimensional environmental monitoring points for each device, and simultaneously deploy infrared monitoring devices and vibration sensors at key protective locations on each device. Simultaneously collect parameters such as temperature, humidity, dust concentration, light intensity, and wind speed through the multi-dimensional environmental monitoring points, and simultaneously collect intrusion data through the infrared monitoring devices and vibration sensors. Using a distributed storage architecture, store environmental parameters categorized by device identifier, collection timestamp, and parameter type, and store intrusion data according to the same categorization dimension, simultaneously constructing a regional dataset containing both environmental parameters and intrusion data. Preprocess the environmental parameters in the regional dataset by using linear interpolation to fill in missing values, removing extreme outliers using the 3σ principle, and standardizing parameters of different dimensions. Simultaneously, preprocess the intrusion data by using the 3σ principle to remove false alarms caused by environmental interference, and combine infrared signal heat source intensity to classify biological size ranges and vibration signal characteristics to further subdivide intrusion types, forming an intrusion dataset.

[0127] Step S2: Based on the regional dataset, conduct time-series statistical analysis on environmental parameters. Use the STL time series decomposition method to identify periodic fluctuation characteristics, calculate correlation coefficients to extract associated trend characteristics, and obtain daily time-period parameter feature clusters through clustering algorithms. Based on the above features, construct environmental common patterns, divide basic time periods according to periodic fluctuation characteristics, and further subdivide independent control periods by combining parameter feature clustering and the similarity of associated trend characteristics. At the same time, select abnormal control periods to form a set of control periods. Extract the environmental parameter feature set for each control period, match and set the core component operation parameters, energy consumption allocation parameters, and water production performance target parameters based on the environmental operation parameter mapping set to form typical operation parameter values.

[0128] Step S3: Define the assessment period covering the stable trend and short-term changes of the environment and break it down into multiple assessment sub-periods; call up the equipment environmental parameters within the assessment period, organize them by sub-period, control period, and equipment identification, and extract the common environmental patterns of each sub-period to construct a related dataset; calculate the deviation, fluctuation frequency, and trend fit of the environmental parameters, obtain a comprehensive stability score through weighted summation, and classify the stability level; match the initial detection period benchmark for different stability levels to balance monitoring accuracy and energy consumption costs.

[0129] Step S4: Call the environmental parameter constraint range and maximum allowable deviation threshold for the current control period of the outdoor water treatment equipment; acquire real-time environmental parameters according to the differentiated detection cycle, and after noise filtering and invalid value supplementation, compare each parameter with the constraint range to determine if there is an environmental anomaly; if an anomaly is determined, combine the environmental operation parameter mapping set with the equipment's historical correction records and service life to determine a personalized correction scheme, send correction instructions and monitor the effect in real time; if the standard is met, record the correction data; if not, fine-tune the parameters and repeat the operation. Count the number of times abnormal environmental parameters occur in each control period for each abnormal device; if the anomaly warning threshold is exceeded, trigger control period correction; extract the occurrence time, deviation amplitude, and duration of abnormal parameters to construct a correction dataset; compare the abnormal parameter values ​​with the parameter fluctuation threshold, marking them as abnormal control period correction or independent control period correction; for the former, cluster to identify stable abnormal periods and supplement or merge abnormal control periods; for the latter, cluster to subdivide the original independent control periods, and reset the environmental parameter constraint range and typical operation parameter values ​​for each sub-period.

[0130] Step S5: Based on the intrusion dataset, count the intrusion frequency at a fixed time granularity, mark potential risk periods, and locate key intrusion areas; cluster and merge potential risk periods to form intrusion defense periods, summarize all periods, and initiate scenario-specific adaptation and integration for overlapping periods, matching intrusion defense execution parameter values. During non-intrusion defense periods, continuously collect intrusion data, count the number of intrusions in each monitoring period, mark monitoring periods to be merged, and filter candidate merged defense periods, prioritizing the period with the shortest time interval as the target defense period and adjusting its start and end times and defense parameters; during non-defense periods, real-time detection of biological intrusions, if they occur, immediately activate emergency defense measures and record data; periodically optimize the division of defense periods based on intrusion data from non-defense periods, and synchronously update all device intrusion prevention and control modules.

[0131] Working principle and its effects:

[0132] This invention solves the problems of adaptability, abnormal response efficiency and biological invasion prevention of outdoor water purification equipment in complex environments, and ultimately achieves a comprehensive improvement in equipment operation performance.

[0133] Environmental parameters are collected from each device in the work area, and the data is categorized and stored according to device identification and timestamp to construct a regional dataset. After missing value imputation, outlier removal, and standardization preprocessing, time-series statistical analysis is used to construct common environmental patterns. Based on this, control sets are divided into independent control periods and abnormal control periods, and typical operating parameters for each period are matched. This process allows the devices to dynamically adjust their operating status according to the regional environmental patterns, effectively avoiding the problem of low water production efficiency caused by fixed parameters, while reducing the wear and tear on core components caused by parameter mismatch. Based on the current control period of the device, typical parameters are called to regulate operation. Differentiated detection cycles are also configured for various environmental parameters according to the stability of the common environmental patterns. Parameters are collected in real time and compared with the constraint range to check for anomalies. If an anomaly is detected, targeted correction operations are performed and the control period is optimized. This approach ensures that anomalies in fluctuating parameters are not missed, avoids redundant energy consumption in monitoring stable parameters, and can accurately adapt to the local abnormal environment of individual devices, further improving operational stability. The intrusion prevention and control module collects intrusion data from devices, preprocesses it to subdivide intrusion types, performs time-series statistical clustering to divide defense periods, and continuously monitors intrusion data during non-defense periods. If the intrusion frequency exceeds the standard during a certain period, the defense period is dynamically adjusted. This logic avoids the high energy consumption of continuous 24-hour defense, while reducing equipment damage and water pollution caused by passive response after biological intrusion, and improving the accuracy of prevention and control and the balance of energy efficiency.

[0134] In summary, this application breaks through the limitations of traditional equipment's fixed operation, unified monitoring, and passive defense by using data-driven dynamic adjustment, comprehensively solving the core pain points of existing equipment, and ultimately enabling outdoor water production equipment to achieve stable, efficient, and safe water supply operation in complex scenarios such as remote water-scarce areas and wilderness camps.

[0135] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. An outdoor water purification equipment environmental adaptation linkage control system, characterized in that, It includes a data hub module, a regulation and correction module, and an intrusion prevention module; The data hub module is used to collect and classify the environmental parameters and intrusion data of each outdoor water treatment device within the working area, and to construct regional datasets and intrusion datasets respectively. The regulation and correction module, based on the regional dataset, performs time-series statistical analysis on the environmental parameters of the working area to obtain common environmental patterns, divides control periods, and matches typical operating parameter values ​​for each control period to regulate the operation of the outdoor water treatment equipment. Furthermore, based on the stability of the common environmental patterns of each outdoor water treatment equipment, it configures differentiated detection cycles for each type of environmental parameter. This is used to perform environmental anomaly checks on the outdoor water treatment equipment based on real-time environmental parameters, determining whether any environmental parameters are abnormal. If abnormalities are found, it performs correction operations for the abnormal outdoor water treatment equipment and corrects the control period division for the abnormal outdoor water treatment equipment through typical statistical analysis. The intrusion prevention module is used to divide the intrusion defense period according to the intrusion dataset, and during the non-intrusion defense period, to determine whether the outdoor water treatment equipment has been invaded by biological forces, so as to dynamically adjust the division of the intrusion defense period.

2. The outdoor water purification equipment environmental adaptation linkage control system as described in claim 1, characterized in that, The steps for obtaining common patterns in the work area environment include: The environmental parameters in the regional dataset are preprocessed, including filling in missing values, removing extreme outliers, and standardizing the units, to obtain a standardized regional dataset. Time series statistical analysis was performed on the environmental parameters of the standardized regional dataset. The STL time series decomposition method was used to split the trend, periodic and residual terms of the environmental parameters. The periodic fluctuation characteristics of the environmental parameters were identified by periodic spectrum analysis and autocorrelation function test. Calculate the correlation coefficients between environmental parameters, and extract the correlation trend characteristics of different environmental parameters by setting a correlation coefficient threshold and testing the consistency with the time series trend. Clustering algorithms are used to cluster the combinations of environmental parameters for each time period of the day, and the parameter features of each time period are extracted and clustered. Based on the periodic fluctuation patterns, correlation trends, and parameter clustering of environmental parameters, a common environmental pattern for the work area is constructed to divide the control period.

3. The outdoor water purification equipment environmental adaptation linkage control system as described in claim 2, characterized in that, The steps of dividing the control period and matching the typical operating parameter values ​​for each control period include: The basic time period is divided according to the characteristics of periodic fluctuations; The basic time period is subdivided by calculating the similarity of parameter feature clusters, and continuous basic time periods of parameter feature clusters with similarity greater than or equal to a preset similarity threshold are merged into independent control time periods. When the cluster similarity of parameter features between basic time periods is less than the preset similarity threshold, if the similarity of the correlation trend features between basic time periods is greater than or equal to the preset similarity threshold, they are merged into independent control time periods. Configure the parameter fluctuation thresholds for each environmental parameter, identify abnormal time points where the values ​​of various environmental parameters exceed the corresponding parameter fluctuation thresholds, perform time-series clustering on the abnormal time points, and obtain potential abnormal time periods for various environmental parameters; filter potential abnormal time periods whose duration is greater than a preset basic time length threshold as the abnormal control time periods for the corresponding environmental parameters; By combining independent control periods and abnormal control periods, a set of control periods is formed. The environmental parameter feature set of each control period is extracted, and the typical operating parameter values ​​of outdoor water treatment equipment are matched based on the environmental operating parameter mapping set.

4. The outdoor water purification equipment environmental adaptation linkage control system as described in claim 1, characterized in that, The steps for configuring differentiated detection cycles for each type of environmental parameter include: Define the assessment period and divide it into multiple assessment sub-periods of equal length, each of which contains a complete set of control periods; The environmental parameters of all outdoor water treatment equipment within the evaluation period are retrieved, categorized by evaluation sub-period, control period, and equipment identification, and the common environmental patterns of each control period under each evaluation sub-period are extracted to construct an associated dataset. For the environmental parameters of each control period under each evaluation sub-cycle, calculate stability indices, including deviation, fluctuation frequency, and trend fit: After standardizing each stability index, the weighted summation method is used to calculate the overall stability score of each type of environmental parameter under the control period of a single assessment sub-cycle, and the average of the overall stability scores of all assessment sub-cycles is taken as the stability score of that type of environmental parameter in the corresponding assessment cycle. The stability levels are determined based on the stability scores of each environmental parameter in the corresponding evaluation period, and then matched with the corresponding testing period.

5. The outdoor water purification equipment environmental adaptation linkage control system as described in claim 4, characterized in that, The deviation refers to the average degree of deviation between the actual collected values ​​of environmental parameters and the typical parameter values ​​in the common environmental pattern of that control period within the evaluation sub-cycle. The fluctuation frequency refers to the number of times within a certain control period, the actual collected value of environmental parameters exceeds the environmental fluctuation range under the common environmental pattern of that control period within the evaluation sub-cycle; The trend fit refers to the degree of overlap between the actual change trend curve of environmental parameters under a certain control period within the evaluation sub-cycle and the periodic fluctuation trend curve in the common environmental pattern of that control period.

6. The outdoor water purification equipment environmental adaptation linkage control system as described in claim 1, characterized in that, The specific steps for performing environmental anomaly testing on outdoor water purification equipment and determining whether there are any abnormalities in environmental parameters include: Call the environmental parameter constraint range of the current control period of the outdoor water treatment equipment, and at the same time obtain the threshold of the number of deviations of the environmental parameters within the control period; According to the configured detection cycle, real-time environmental parameters are obtained. After the real-time environmental parameters are processed by data standardization, they are compared with the environmental parameter constraint range of the current control period parameter by parameter. If the real-time value of an environmental parameter is within the corresponding environmental parameter constraint range, the environmental parameter is determined to be normal; otherwise, the environmental parameter is determined to be potentially abnormal and is marked as a potentially abnormal parameter. The number of times potential abnormal parameters occur during the current control period is counted. If the number of occurrences exceeds the deviation threshold, the current environmental parameter is determined to be an abnormal environmental parameter; otherwise, it is determined to be a transient fluctuation.

7. The outdoor water purification equipment environmental adaptation linkage control system as described in claim 1, characterized in that, The specific steps for dividing the control period of the corrective outdoor water treatment equipment include: For each abnormal outdoor water treatment device, the number of times abnormal environmental parameters occur during each control period is counted. If the number exceeds the abnormal warning threshold, the control period correction for the abnormal outdoor water treatment device is triggered. Based on the regional dataset, the occurrence time of abnormal environmental parameters of abnormal outdoor water treatment equipment, the deviation between abnormal environmental parameters and the corresponding control period constraint range, and the duration of a single abnormality are extracted to construct a corrected dataset. For each abnormal environmental parameter value, compare it with the corresponding parameter fluctuation threshold. If it is greater than the corresponding parameter fluctuation threshold, mark it as an abnormal control period correction; otherwise, mark it as an independent control period correction. For abnormal environmental parameters marked as requiring correction during abnormal control periods, a density clustering algorithm is used to perform temporal clustering of their occurrence times to identify continuously occurring stable abnormal periods. The total duration of the stable abnormal periods is calculated. If it exceeds a preset basic time length threshold, it is determined to be a newly added abnormal control period that needs to be supplemented. If the newly added abnormal control period overlaps with the existing abnormal control period, the overlapping abnormal control periods are merged and their environmental parameter constraint ranges are adjusted. Otherwise, environmental parameter constraint ranges and corresponding typical operating parameter values ​​are set separately for them. For abnormal environmental parameters marked as being corrected for independent control periods, the original independent control periods to which they belong are extracted. A clustering algorithm is used to combine the occurrence time and deviation of the abnormal environmental parameters within the independent control period, and the original independent control period is subdivided into multiple independent control sub-periods. The environmental parameter constraint range is reset for each independent control sub-period, and typical operating parameter values ​​that are suitable for the characteristics of the sub-period are retrieved from the environmental operating parameter mapping set.

8. The outdoor water purification equipment environmental adaptation linkage control system as described in claim 1, characterized in that, The steps for dividing intrusion prevention time periods include: For each intrusion type, the initial time period is divided according to a fixed time granularity. The intrusion frequency of each initial time period is counted. The initial time period with an intrusion frequency greater than a preset frequency threshold is marked as a potential risk period. For each type of intrusion, the number of intrusions at different device locations during the potential risk period is counted, the proportion of intrusions at each location to the total number of intrusions during that period is calculated, and the key intrusion areas are located based on the intrusion proportion. Density clustering algorithm is used to cluster and merge potential risk periods of the same intrusion type as intrusion defense periods; For potential risk periods that are isolated after clustering, if their key intrusion areas coincide with adjacent intrusion defense periods, they are merged into the adjacent intrusion defense periods.

9. The outdoor water purification equipment environmental adaptation linkage control system as described in claim 1, characterized in that, The steps for dynamically adjusting the division of intrusion prevention time periods include: During non-intrusion defense periods, intrusion data within the work area is continuously collected to construct a non-defense period intrusion dataset and conduct multi-dimensional statistical analysis: for each intrusion type or intrusion device location, the timestamp of each intrusion under that intrusion type or intrusion device location is tracked one by one, and the monitoring period range to which each intrusion timestamp belongs is defined, and the total number of intrusions of that intrusion type or intrusion device location within that monitoring period range is counted. If the total number of intrusions of a certain type or the location of the intruding device within a certain monitoring period exceeds a preset frequency threshold, it is marked as a monitoring period to be merged. Based on the timestamp of the intrusion that occurred during the monitoring period to be merged, intrusion defense periods with the same intrusion type or intrusion device location as the monitoring period to be merged are selected in the current intrusion defense period. The target intrusion defense period is located by combining the time interval between the monitoring period to be merged and the intrusion defense period, and the start and end times of the target intrusion defense period are updated and adjusted.

10. An environmental adaptation linkage control method for outdoor water purification equipment, implemented based on the environmental adaptation linkage control system for outdoor water purification equipment as described in any one of claims 1 to 9, characterized in that, include: Step S1: Collect and classify the environmental parameters and intrusion data of each outdoor water treatment device in the work area, and construct the regional dataset and the intrusion dataset respectively; Step S2: Based on the aforementioned regional dataset, perform time-series statistical analysis on the environmental parameters of the work area, obtain common environmental patterns in the work area, divide control time periods, and match typical operating parameter values ​​for each control time period; Step S3: Based on the current control period of the outdoor water purification equipment, call typical operating parameter values ​​to regulate the operation of the outdoor water purification equipment, and configure differentiated detection cycles for each type of environmental parameter according to the stability of the common environmental mode of each outdoor water purification equipment. Step S4: Based on real-time environmental parameters, perform an environmental anomaly check on the outdoor water production equipment to determine whether there are any anomalies in the environmental parameters. If there are, perform an abnormal outdoor water production equipment correction operation and correct the control period division of the abnormal outdoor water production equipment through typical statistical analysis. Step S5: Based on the intrusion dataset, divide the intrusion defense period into time periods, and during the non-intrusion defense period, determine whether the outdoor water treatment equipment has been invaded by biological forces, so as to dynamically adjust the division of the intrusion defense period.

Images