Operation method of a fabric cleaning and disinfecting machine for controlling multidrug-resistant bacteria

Abstract

This invention discloses a method for operating a fabric cleaning and disinfection machine for controlling multidrug-resistant bacteria, specifically relating to the field of fabric cleaning and disinfection technology. The method involves acquiring the contamination intensity level, fabric material type, and target bacterial species spectrum information of the target fabric to construct a contamination source information set; calling a preset disinfection response parameter model to determine the washing temperature, washing time, and disinfectant type and concentration; retrieving a matching set of cleaning programs from a database based on the fabric type and its temperature and chemical resistance properties, and dynamically adjusting them; monitoring the water temperature and detergent concentration in real time during the washing process, and adjusting the washing parameters according to a feedback control model; after washing, extracting and analyzing the temperature deviation and critical inhibition threshold of the target bacterial species during the washing stage, and updating the disinfection response model based on the analysis results. This invention's method can achieve highly efficient killing and disinfection of multidrug-resistant bacteria through adaptive optimization, and is suitable for fabric treatment needs in the medical, elderly care, and public health fields.

Description

Technical Field

[0001] This invention relates to the field of fabric cleaning and disinfection technology, specifically to a method for operating a fabric cleaning and disinfection machine for controlling multidrug-resistant bacteria. Background Technology

[0002] This paper proposes a method for operating a fabric cleaning and disinfection machine that can intelligently regulate cleaning and disinfection parameters under the background of multiple drug resistance characteristics of microorganisms, while taking into account both fabric protection and energy saving, so as to achieve efficient control of multidrug-resistant bacteria and safe treatment of fabrics. Summary of the Invention

[0003] The purpose of this invention is to provide an operating method for a fabric cleaning and disinfection machine for controlling multidrug-resistant bacteria, in order to address the shortcomings of the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a method for operating a fabric cleaning and disinfection machine for controlling multidrug-resistant bacteria, comprising:

[0005] S100: Obtain the pollution intensity level, fabric material type, and target bacterial species spectrum information of the target fabric, and construct the pollution source information set P;

[0006] S200: Based on the pollution source information set P, call the preset disinfection response parameter model to determine the washing temperature T, washing and disinfection action time t, and disinfectant type and concentration parameter C;

[0007] S300: Based on the fabric material type and its temperature and chemical resistance properties, retrieve the matching set of cleaning programs W from the washing machine database and dynamically adjust it according to disinfection requirements;

[0008] S400: During the main washing program, it monitors changes in water temperature and detergent concentration in real time and adjusts washing parameters according to a preset feedback control model.

[0009] S500: Extracts and analyzes the dynamic temperature deviation value during the washing stage of the washing and disinfection process and the critical inhibition threshold of the target bacteria species in the residual bacteria detection data, and automatically updates the disinfection response parameter model of fabric washing based on the analysis results.

[0010] Preferably, in S200, the disinfection response parameter model is a multivariate fitting model constructed based on a pollution source information set. The pollution source information set includes pollution intensity level, fabric material type, and target bacterial species spectrum information. The multivariate fitting model is constructed through the following steps:

[0011] Historical fabric washing sample data were organized, and the pollution intensity level, fabric material type and target bacterial species spectrum information corresponding to each batch were extracted as input variables;

[0012] Extract the actual operating parameters for the corresponding batch, including washing temperature, washing and disinfection time, and disinfectant type and concentration, as the target output variables;

[0013] Multidimensional regression modeling was performed on the input and output data to construct a washing temperature prediction function, a time prediction function, and a disinfectant concentration recommendation function.

[0014] In the modeling process, a tolerance adjustment mechanism and a weighting factor are introduced to control the acceptable fluctuation range of temperature, time and disinfectant concentration and the weighting influence of each input variable, respectively.

[0015] Cross-validation and error feedback correction are performed on the model results to achieve dynamic adaptation of disinfection response parameters.

[0016] Preferably, in S300, the dynamic adjustment based on disinfection requirements includes:

[0017] Extract the washing temperature, washing and disinfection time, and disinfectant type and concentration output from the disinfection response parameter model;

[0018] The standard programs that match the fabric material type in the preset cleaning program set are screened to form an initial candidate program set;

[0019] Adjust the temperature rise curve, disinfection duration, and disinfectant injection timing in the initial candidate program according to the disinfection requirement level of the target bacterial species.

[0020] Increase the program's set temperature without exceeding the fabric's temperature resistance limit;

[0021] The frequency and rhythm of the rinsing process are dynamically adjusted to meet the requirements of different types of disinfectants for residue inhibition.

[0022] The adjusted program parameters are combined to form the final running program, which is used to execute this fabric cleaning and disinfection task.

[0023] Preferably, in S400, adjusting the washing parameters according to the preset feedback control model includes:

[0024] A composite feedback control model incorporating fuzzy control and proportional-integral-derivative control is constructed, with the water temperature, detergent concentration, and disinfection time collected in real time during the washing process as input variables.

[0025] Set target values ​​for washing parameters, including target water temperature, target detergent concentration, and desired disinfection time;

[0026] Calculate the deviation between the current parameter and the target value, and determine the level of parameter deviation through the fuzzy inference module;

[0027] Based on the deviation level, the corresponding adjustment command direction is output and input into the proportional-integral-derivative controller to generate a continuous control signal.

[0028] The control signal is used to adjust the heater output, detergent dosing rate, stirring frequency, or washing stage time to dynamically correct deviations.

[0029] Preferably, in S500, the calculation steps for the dynamic temperature deviation value include:

[0030] During the main washing process, the current water temperature data is acquired at a fixed sampling period and recorded to form a time series: ;in, to This represents the time points from the start of washing to the completion of disinfection, where n represents the total number of time points; it also records the target constant temperature value output by the disinfection response parameter model during this operation, denoted as . ;

[0031] Based on the actual temperature of each sampling point With target temperature The difference between them is used to calculate the instantaneous temperature deviation sequence. : Subsequently, the deviation throughout the process was normalized and averaged to obtain the dynamic temperature deviation value ΔT_avg for this washing stage, denoted as: .

[0032] The preferred calculation steps for the critical inhibition threshold of the target bacterial species are as follows:

[0033] After the fabric washing and drying are completed, residual bacterial data are collected after this operation, and the survival status of the target bacterial species in the residual samples after washing is identified.

[0034] Set a target bacterium before operation The initial bacterial load was ;

[0035] After washing, the residual bacterial load was measured to be... Then this operation will affect The actual suppression rate is defined as: ;

[0036] Pre-set recommended inhibition thresholds for each type of common multidrug-resistant bacteria. ; each target bacterium The actual suppression rate is compared with the recommended threshold to form a difference. The expression is: ;

[0037] For all target bacterial species By performing a weighted average and combining the hazard level weights of each bacterial species, the critical inhibition threshold of the target bacterial species is obtained.

[0038] Preferably, the dynamic temperature deviation value and the critical suppression threshold are converted into a comprehensive feature vector. The comprehensive feature vector is used as the input of the machine learning model. The machine learning model uses the error score label of the disinfection response parameter model for the control performance of this operation for each set of comprehensive feature vectors as the prediction objective. The training objective is to minimize the sum of the prediction errors of all the error score labels of the disinfection response parameter models for the control performance of this operation. The machine learning model is trained until the sum of prediction errors converges and the model training stops. The error score value of the disinfection response parameter model for the control performance of this operation is determined according to the model output result. The machine learning model is a multinomial regression model.

[0039] Preferably, when the error score E_model of the disinfection response parameter model for the control performance of this operation exceeds the set threshold E_thresh, it is determined that there is a configuration deviation in the disinfection response parameter model, and the automatic update logic is triggered.

[0040] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0041] 1. This invention achieves multi-parameter dynamic optimization of the fabric cleaning and disinfection process by constructing a disinfection response parameter model based on a pollution source information set and combining it with a real-time monitoring and feedback control mechanism. The system can not only intelligently set the washing temperature, time, and disinfectant concentration according to the fabric material and target bacterial characteristics, but also automatically sense temperature fluctuations and changes in chemical concentration during operation, adjusting the washing strategy in real time to ensure that the disinfection effect meets standards while effectively protecting the fabric from damage.

[0042] 2. This invention introduces a residual bacteria analysis and model self-learning mechanism after the washing process, enabling feature extraction and comprehensive analysis of dynamic temperature deviations and actual inhibition results, and optimizing subsequent operating parameters accordingly. This closed-loop update strategy significantly improves the system's adaptability and inhibition stability against multidrug-resistant bacteria, possessing significant technical advantages such as precise disinfection, strong fabric compatibility, and optimized energy efficiency control. It is particularly suitable for scenarios with high hygiene control requirements, such as medical care, elderly care, and public health. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0044] Figure 1Flow chart of the method of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] Example 1, please refer to Figure 1 As shown in this embodiment, the operating method of the fabric cleaning and disinfection machine for controlling multidrug-resistant bacteria includes:

[0047] S100: Obtain the pollution intensity level, fabric material type, and target bacterial species spectrum information of the target fabric, and construct the pollution source information set P;

[0048] S200: Based on the pollution source information set P, call the preset disinfection response parameter model to determine the washing temperature T, washing time t, disinfectant type and concentration parameter C;

[0049] S300: Based on the fabric type and its temperature and chemical resistance properties, retrieve the matching set of cleaning programs W from the washing machine database and dynamically adjust it according to disinfection requirements;

[0050] S400: During the main washing program, it monitors changes in water temperature and detergent concentration in real time and adjusts washing parameters according to a preset feedback control model.

[0051] S500: Extracts and analyzes the dynamic temperature deviation value during the washing stage of the washing and disinfection process and the critical inhibition threshold of the target bacteria species in the residual bacteria detection data, and automatically updates the disinfection response parameter model of fabric washing based on the analysis results.

[0052] In this invention, the first step is to extract information and identify contamination characteristics of the target fabric entering the cleaning process to construct a contamination source information set for subsequent intelligent operation control. This step, as a crucial foundational step before the disinfection process, directly affects the scheduling strategy of subsequent cleaning and disinfection parameters, the matching accuracy of disinfectants, and the efficiency of equipment resource regulation.

[0053] Specifically, the pollution source information set includes the following three categories of key attribute information: fabric pollution intensity level, fabric material type, and target bacterial species spectrum information. The acquisition methods and processing procedures for each type of information are as follows:

[0054] Fabric stain intensity rating primarily characterizes the microbial load and organic stain content on the fabric surface and within the fibers, and is an important indicator of the initial hygiene status of the fabric. Its assessment can be based on a combination of the following three methods:

[0055] Source identification method: Predictive assessment is made by obtaining information on the location and cycle of fabric use. For example, fabrics from intensive care units, isolation wards, or infectious disease departments are assumed to have a high level of contamination; fabrics from general departments or nursing facilities are considered medium level; and fabrics from ordinary home clothing or ordinary dormitory areas are considered low level.

[0056] Sensor analysis method: Before the fabric enters the washing process, the device uses built-in spectral, image, or odor recognition sensor modules to initially screen the fabric for contaminants. For example, it detects the signal intensity of fluorescence reactions and organic protein residues, and automatically determines the contamination intensity based on a preset threshold model within the device.

[0057] Manual labeling and learning method: The operator selects the pollution level (such as light, moderate, heavy) on the interface before putting the fabric in, and combines the results of previous washing residual bacteria monitoring to train the model and form a dynamic adjustment system for pollution level.

[0058] The above method can be used to classify pollution intensity levels into 3 to 5 levels. The system uses a hierarchical numbering system. For example, pollution level P∈{1, 2, 3} corresponds to light, moderate and heavy pollution, respectively.

[0059] Fabric material identification is primarily used to determine its temperature resistance, chemical resistance, and tensile strength to prevent damage in high-temperature or strong chemical environments. Fabric material identification can be performed using the following methods:

[0060] RFID coding identification: For fabrics with embedded electronic tags (such as RFID), the type of fabric material can be obtained by scanning and reading the coding information, such as pure cotton, polyester, nylon, medical non-woven fabric, etc.

[0061] Image texture and fiber analysis method: The texture of the fabric fiber image is extracted by the built-in camera system or microscope sampling device, and the material type is determined by the image classification through a deep learning model.

[0062] Manual input and system memory method: When the device first recognizes an unknown fabric, the operator can manually select the fabric type, and the system saves the image and parameters of that type of fabric for subsequent recognition and automatic comparison.

[0063] Different material types are represented by codes, such as cotton as F1, polyester as F2, non-woven fabric as F3, wool as F4, etc. The system establishes a matrix-like relationship between material properties and washing constraints to limit temperature, disinfectant type and mechanical program.

[0064] The types of multidrug-resistant bacteria have a crucial impact on the selection of disinfectants and the duration of action; therefore, it is essential to determine the target bacterial spectrum as much as possible before operation. This information can be obtained through the following methods:

[0065] The system uses a location risk spectrum matching method: It pre-defines high-risk locations and corresponding bacterial species risk models, such as associating MRSA and CRE with infectious disease wards; Pseudomonas aeruginosa with burn wards; and Acinetobacter baumannii with long-term care facilities. The system then matches relevant bacterial species spectra based on the fabric origin label.

[0066] Historical washing residual bacteria detection retrospective method: The equipment is equipped with periodic sampling and culture devices. By combining the data of previous residual bacteria detection, the dominant bacterial groups that the current batch may carry can be inferred.

[0067] The bacterial species information is modeled using a spectrum numbering method, such as G1 representing Staphylococcus aureus, G2 representing Pseudomonas aeruginosa, and G3 representing Acinetobacter baumannii. The system records the target bacterial spectrum G = {G1, G3} in a set manner.

[0068] After acquiring the above three types of information, the pollution level number P, fabric material type code F, and target bacterial species spectrum G are combined to form a pollution source information set InfoSet = {P, F, G}. The system uses this information set as input to the disinfection response parameter generation module, serving as the core basis for parameter scheduling.

[0069] For example, in a real-world case, a batch of fabrics comes from an infectious disease ward, is frequently used, and is marked as contamination level P=3; its material is medical non-woven fabric, which is sensitive to temperature, denoted as F=F3; it is known that the ward has a risk of infection with Acinetobacter baumannii and Pseudomonas aeruginosa, corresponding to G = {G2, G3}, then the contamination source information set is: InfoSet = {3, F3, {G2,G3}}.

[0070] Upon receiving this information set, the system will automatically disable the high-temperature sterilization program and switch to a low-temperature long-lasting disinfection scheme using peracetic acid or compound quaternary ammonium salt. At the same time, it will extend the action time and set multiple soaking stages in the program to improve the kill rate of drug-resistant bacteria and avoid damage to the fabric.

[0071] In summary, by systematically identifying and integrating models of pollution levels, fabric materials, and bacterial strains, precise and differentiated control of the fabric cleaning and disinfection process can be achieved, which is one of the fundamental technical aspects of this invention.

[0072] In this invention, after the construction of the pollution source information set (denoted as P) is completed, the fabric washing and disinfection response stage begins. The core of this stage lies in automatically determining the optimal washing and disinfection process configuration parameters based on various input parameters of the pollution source information set by calling a preset disinfection response parameter model. These parameters include, but are not limited to, washing temperature T, washing time t, disinfectant type and its concentration parameter C.

[0073] The disinfection response parameter model described in this invention is a dynamic matching and optimization model under multivariate conditions, and has the following three core functions:

[0074] After inputting the pollution source information set P, it can quickly output the cleaning configuration parameter set (T, t, C).

[0075] It can balance multiple objectives based on microbial characteristics, fabric tolerance, and pollution level;

[0076] It possesses the ability to continuously learn and dynamically update, thereby improving long-term adaptability and model accuracy.

[0077] In this invention, the model is constructed using a pollution source information set P as input and outputs a parameter set (T, t, C), that is:

[0078] Input P = {P_level, F_type, G_species}, where:

[0079] P_level represents the pollution intensity level, with a value ranging from 1 to 5;

[0080] F_type represents the fabric material type, such as pure cotton, polyester, non-woven fabric, etc.

[0081] G_species represents the target microbial spectrum, which can be a collection of single or multiple multidrug-resistant bacteria;

[0082] Output parameter set:

[0083] T indicates the recommended washing temperature, in degrees Celsius;

[0084] t represents the washing and disinfection time, in minutes;

[0085] C indicates the type of disinfectant selected and its recommended concentration, expressed as a percentage by weight (w / v%) or a concentration by weight (mg / L).

[0086] This model is constructed by combining regular mapping and multidimensional regression to achieve parameter transformation from P to (T, t, C).

[0087] First, a large amount of real-world cleaning case data was collected, including the contamination level, fabric type, bacterial species, temperature, time, type and concentration of disinfectant used, and residual bacterial test results after the corresponding batch cleaning (e.g., colony reduction ratio, target bacterial detection rate, etc.). Based on this data, a sample set containing input variables and target output variables was constructed.

[0088] The goal is to achieve sterilization effectiveness (e.g., target bacterial kill rate ≥ 99.99%) while avoiding damage to the fabric material and controlling overall energy and resource consumption.

[0089] First, a set of basic rule mapping tables is established. These rules, based on expert experience, industry standards, and existing scientific research data, define the basic parameter configuration ranges for different contamination levels and bacterial species. For example:

[0090] For cotton fabrics with a contamination level of 3 and the target bacterial species being MRSA, the recommended temperature is 60–70°C, the contact time is 15–30 minutes, and the concentration of quaternary ammonium salt disinfectant is 500–1000 mg / L.

[0091] For nonwoven fabrics with a contamination level of 5 and a combination of Pseudomonas aeruginosa and Acinetobacter baumannii, the recommended temperature is no higher than 50°C, the contact time needs to be extended to 40–60 minutes, and a low-temperature broad-spectrum disinfectant containing peracetic acid should be used at a concentration of 1000–2000 mg / L.

[0092] This set of rules forms the initial matching matrix, which is used to constrain the model parameter space and provide an initial fitted surface.

[0093] Based on the rule mapping, a continuous response relationship function is further established using weighted multivariate regression analysis, that is, the model is defined as a multi-input single-output or multi-output mapping problem.

[0094] Let the pollution level P_level be the input variable. ;

[0095] Fabric material type F_type is mapped from a categorical variable to a numerical variable. ;

[0096] The bacterial species spectrum G_species is converted into multiple input dimensions through one-hot encoding. to , representing the tolerance score of each bacterial species;

[0097] Let T, t, and C be the objective functions. , , ;

[0098] Finally, three sets of fitting functions are constructed:

[0099] → Used for temperature prediction;

[0100] → Used for time prediction;

[0101] → Used to recommend disinfectant types and concentrations.

[0102] The above function, through sample training and residual optimization, yields the optimal fitting parameters under the least squared error. Regularized regression is used to control model overfitting, and cross-validation is introduced to improve generalization ability.

[0103] To ensure that the model's output parameters are tolerant to fabric safety and sterilization reliability, a tolerance range is introduced in each output dimension. For example:

[0104] The temperature output T can fluctuate by ±3°C.

[0105] The time output t can fluctuate by ±10%;

[0106] The concentration of disinfectant C can deviate from the permissible concentration by ±15%.

[0107] If the bacterial kill score corresponding to a certain output configuration does not reach the set threshold (e.g., sterilization score <95%), the model will provide feedback correction for that point and update the fitted surface using neighborhood interpolation.

[0108] In addition, the model assigns different weights to the input parameters. The default bacterial species spectrum has the greatest impact on the output, followed by the contamination level, and finally the fabric type. The weight ratios are as follows:

[0109] G_species (species spectrum): 0.5;

[0110] P_level (pollution level): 0.3;

[0111] F_type (fabric type): 0.2;

[0112] This weighting factor can be dynamically updated based on feedback from practical applications, enabling personalized optimization of the model.

[0113] The response model in this invention has a continuous learning function. After each run, the system collects information on residual bacteria in the washing batch and fabric integrity evaluation data, re-evaluates the effect of the current parameter configuration, and uses a gradient descent strategy to fine-tune the model parameters to enhance the model's adaptability.

[0114] The model update follows the principle of "stable output and local iteration", that is, it only corrects the local areas with large prediction errors without interfering with the overall fitting structure, thereby ensuring both the stability and sensitivity of the response model.

[0115] After the model completes the calculation, the system will output the specific running parameters:

[0116] The recommended washing temperature is T (e.g., 62°C);

[0117] The recommended duration of action is t (e.g., 28 minutes);

[0118] The recommended disinfectant is a certain type of compound quaternary ammonium salt solution, with a recommended concentration of 850 mg / L.

[0119] The control system automatically configures the equipment to execute programs based on these outputs, completing safe and efficient disinfection treatment of different types of fabrics.

[0120] In this invention, after acquiring the pollution source information set and determining the washing temperature T, contact time t, disinfectant type, and concentration parameter C through a disinfection response parameter model, the system enters the cleaning process program adjustment stage. The key task of this stage is to retrieve a matching cleaning program set W from the washing machine database based on the fabric type and its temperature and chemical resistance properties, and to dynamically adjust this program set according to the current disinfection requirements to meet the dual requirements of sterilization and fabric protection.

[0121] This process consists of two main stages:

[0122] The retrieval and initialization of the standard procedure set W, and the dynamic adjustment and adaptation of the procedure set based on disinfection requirements. These two processes are described in detail below.

[0123] The retrieval and initialization of the standard cleaning procedure set W are as follows:

[0124] The washing machine has multiple preset standard washing programs stored in a local or remote database. Each program consists of a series of parameters, including but not limited to:

[0125] Initial inlet water temperature and heating rate;

[0126] Total duration and segmented structure of main wash and pre-wash;

[0127] The timing of detergent or disinfectant injection;

[0128] Stirring intensity and rhythm;

[0129] Frequency and intensity of the dehydration stage;

[0130] Number of flushing cycles;

[0131] Temperature upper limit and mechanical motion constraints.

[0132] Each program is bound to a specific fabric material type and function tag, such as "Cotton High-Temperature Standard Wash," "Synthetic Fiber Sensitive Mode," "Medical Fabric Sterilization Program," and "Heavily Soiled Acid-Resistant Program." Program metadata is stored in a structured format for easy filtering and matching based on conditions.

[0133] Once the system obtains the pollution source information set P, especially including the fabric material type F (such as pure cotton, polyester, non-woven fabric, wool, etc.), it first uses material index matching to initially screen the available program set WO and constructs a standard program candidate set.

[0134] For example: if the fabric type is F = F1 (pure cotton), the system will filter all programs marked as "F1 compatible" from the database to form a set WO = {W1, W2, W4, W6};

[0135] If the fabric type is F = F3 (non-woven fabric), then only select programs with low-temperature protection and gentle mechanical action, such as WO = {W7, W9}.

[0136] This step ensures that the selected program is safe for the fabric under default conditions and will not cause material damage due to high temperature or high mechanical strength.

[0137] The dynamic adjustment of the program set W based on disinfection requirements is as follows:

[0138] After the standard procedure set W0 is established, it needs to be dynamically adjusted to meet the specific disinfection requirements of this operation in order to improve the ability to kill target multidrug-resistant bacteria. This stage employs the following five-step strategy for dynamic procedure configuration:

[0139] The system extracts the corresponding disinfection level requirements based on the G (target bacterial species spectrum) in the pollution source information set and the output results (T, t, C) of the response parameter model. For example:

[0140] If the target bacterium is Pseudomonas aeruginosa, the disinfection requirement level is set to D=high.

[0141] If the target bacterium is a single non-spore-forming bacterium, the disinfection requirement level is D=medium;

[0142] If bacterial spores (such as Clostridium difficile) are involved, then D = extremely high.

[0143] The system uses D as the primary driving variable for dynamic adjustment, controlling subsequent strategies.

[0144] The initial heating rate and maximum temperature set in the program will be adjusted based on the T value:

[0145] If the model outputs a recommended temperature T′ that is higher than the upper limit of the original program temperature, the system will perform a temperature curve reset operation.

[0146] The temperature adjustment control formula is: New temperature target = max{Original program temperature, Model recommended temperature T′}, but it must not exceed the upper limit of the fabric's temperature resistance. ;in This information is derived from a fabric property table, for example, 55°C for non-woven fabrics and 90°C for cotton. If the limits are exceeded, priority is given to ensuring fabric safety, and the disinfectant's contact time is extended in subsequent stages to compensate.

[0147] Based on the action time t′ output by the model, the duration of the main wash stage and the disinfection soaking stage of the program is stretched. The system will insert a "high-concentration settling section" or a "low-speed stirring and heat preservation section" into the washing program structure to ensure that the disinfectant continues to act in the high-load zone.

[0148] The duration adjustment logic is as follows:

[0149] If t′ is longer than the current total program duration, then insert a delay into the main shuffle segment or the middle segment;

[0150] If t′ is shorter than the original program duration, then equivalent sterilization conversion should be performed based on the recommended concentration of disinfectant, allowing for a shorter time.

[0151] This invention supports flexible disinfectant injection timing and multiple rinsing combinations:

[0152] If using a high-concentration, low-temperature disinfectant, the injection point should be set in the low-speed stirring section.

[0153] If volatile oxidants (such as peracetic acid) are used, the exposure period should be shortened and the fabric rinsed quickly after injection to prevent corrosion.

[0154] The system performs three-parameter linkage adjustments on the disinfectant injection time point T_inject, retention time t_hold, and number of rinses n_rinse to form the most effective disinfectant management path for the target strain.

[0155] After completing the above adjustments, the system integrates the original standard program structure with the dynamic adjustment factor to form a new customized program structure W′: W′ = W_i + ΔT + Δt + ΔC + injection strategy + rinsing strategy; where ΔT represents the temperature curve adjustment amount, Δt is the duration compensation value, and ΔC is the disinfectant concentration adjustment factor. All adjustments are written into the washing machine control chip by the controller, forming a traceable washing record for the current batch.

[0156] To prevent system imbalance caused by repeated parameter adjustments, the present invention also designs the following safety control mechanism:

[0157] When disinfection objectives conflict with fabric protection, the system will select a non-destructive solution for the fabric and compensate by increasing the dosage or extending the time. During the dynamic adjustment process, the system will simultaneously assess changes in the consumption of resources such as water, electricity, and detergent to avoid exceeding resource limits in a single wash. All parameter adjustments will generate an operation log, which will serve as the data basis for subsequent model updates and controller firmware upgrades.

[0158] In this invention, during the execution of the main washing program, the system not only executes the control process based on static set values, but also monitors key operating parameters such as water temperature, water quality, conductivity, and detergent concentration in real time through an embedded sensing system. Furthermore, it dynamically fine-tunes key washing process parameters through a feedback control model to improve the disinfection effect of controlling multidrug-resistant bacteria and ensure the physical integrity of the fabric material and optimal energy efficiency of the system operation.

[0159] The core of this process lies in constructing a feedback control model. This model integrates real-time data collected during the washing process with preset expected values, dynamically adjusts system operating parameters, and achieves multi-variable closed-loop control. The following section elaborates on the construction principles and adjustment mechanisms of the feedback model.

[0160] This invention employs an improved fuzzy-proportional-integral-derivative (Fuzzy-PID) control model to construct a washing feedback control system. This model integrates the real-time error adjustment capability of a traditional PID controller with the multi-objective decision logic of a fuzzy controller, making it suitable for applications involving dynamic adjustment of multiple parameters in nonlinear systems.

[0161] The target variables for control include:

[0162] Water temperature T(t): Current water temperature;

[0163] Detergent concentration C(t): The mass concentration of surfactant in the solution;

[0164] Disinfectant contact time : The cumulative time of action of the active ingredients at the current stage;

[0165] Stirring intensity S(t): Motor drive frequency or torque index;

[0166] The system's expected value is derived from the output of the response parameter model established in the previous step and is set as the target value:

[0167] Desired temperature: ;

[0168] Expected concentration: ;

[0169] Expected duration of action: ;

[0170] During operation, the system collects the current actual values ​​T(t) and C(t) in real time through sensors. The deviation is calculated after comparing it with the expected value. , , .

[0171] The system predefines several fuzzy language sets (such as "temperature is too low", "concentration drops rapidly", "temperature fluctuates violently", etc.) and establishes membership functions to map the actual deviations ΔT, ΔC, etc., into fuzzy levels.

[0172] For example: At that time, the membership degree corresponding to "low temperature" is 0.85; At that time, the membership degree corresponding to "rapid decrease in concentration" was 0.90.

[0173] Based on these fuzzy inputs, the system uses a fuzzy inference rule base to determine the direction and intensity of the control output.

[0174] Some examples of rules are as follows:

[0175] If the temperature is too low and the concentration is normal, then increase the heating power (medium).

[0176] Rapid decrease in IF concentration AND normal temperature THEN Delayed rinsing;

[0177] If the temperature fluctuates drastically, then the heating rate will be slowed down.

[0178] Fuzzy rules are used to determine the direction of the control strategy, while the fine-tuning is done by the PID controller.

[0179] The PID controller uses a three-term error superposition model, namely:

[0180] Where: e(t) is the current deviation value (e.g., ΔT); These are the proportional, integral, and derivative coefficients, set according to experience and measured parameters; U(t) is the control output, such as the heater power adjustment percentage or the detergent pump speed correction amount.

[0181] The output level of the fuzzy logic controller directly affects the dynamic adjustment of the coefficients in the PID controller, thereby realizing the fuzzy-PID linkage response.

[0182] After the feedback control model is established, the following parameters are dynamically adjusted during actual operation:

[0183] The system collects water temperature T(t) in intervals of 1 to 5 seconds and compares it with the target value. Comparison. If the temperature deviation ΔT exceeds the set tolerance (e.g., ±1.5°C), the temperature control circuit will be triggered immediately.

[0184] ΔT>+1.5°C (Temperature too high): The system reduces heater power, or performs cold water replenishment if necessary;

[0185] (Low temperature): The system increases the heater output while reducing the drum agitation frequency to reduce heat loss.

[0186] Temperature control can maintain a stable water temperature. Within.

[0187] The detergent concentration C(t) is detected by a combination of conductivity and color sensors. If the deviation ΔC > 100 mg / L, the system will deliver a micro-pulse of detergent to the pump.

[0188] During the main wash phase, the dosage may be adjusted every 3 minutes, with the maximum single adjustment not exceeding 5% of the total dosage;

[0189] If the concentration continues to decrease, the system will initiate a "delayed flushing" procedure to postpone the start time of the next flushing segment in order to extend the effective contact time.

[0190] The system according to Calculate whether the current cumulative disinfection time has reached the threshold. If the efficiency decreases due to low temperature or insufficient concentration, the system will:

[0191] Automatically extend the runtime of the current cleaning phase; or insert additional buffer segments to achieve time compensation, ensuring that the total action time meets the model's recommended value.

[0192] By reading the motor feedback frequency and torque values, the drum load status is determined, and the stirring rhythm is adjusted in conjunction with temperature and concentration parameters. For example:

[0193] When the temperature is low but the concentration is high, the stirring frequency should be increased appropriately to enhance the physical effect;

[0194] When the temperature is high and the concentration is low, reduce the stirring intensity to avoid excessive release of chemical activity.

[0195] The system can select a stirring mode (such as alternating forward and reverse, high-frequency impact, or low-speed suspension) based on the strain resistance tag to optimize the sterilization effect.

[0196] The feedback control model in this invention supports adaptive updates. After completing a washing cycle, the system automatically records the trajectory of key parameter changes, control response logs, and residual bacteria information after washing, forming an operation record set.

[0197] Through "deviation attribution analysis" and "control response learning", the system can iteratively correct the following:

[0198] Adjust the membership function range in the fuzzy controller;

[0199] Optimize PID coefficients to suit the needs of different fabrics or bacterial strains;

[0200] Identify the impact of external factors such as ambient temperature and water hardness on system stability, and improve the robustness of full-cycle control.

[0201] In this invention, to improve the control of multidrug-resistant bacteria during fabric washing, the system collects and analyzes key dynamic data from the operation after the washing and disinfection process is completed, particularly:

[0202] The dynamic temperature deviation during the washing stage, and the critical inhibition threshold of the target bacteria species in the residual bacteria detection data.

[0203] By jointly analyzing the two feature parameters from different dimensions, the sterilization effect of the parameter configuration in this operation can be quantified, thereby enabling automatic updating and self-learning optimization of the disinfection response parameter model.

[0204] The steps for extracting and calculating dynamic temperature deviation values ​​include:

[0205] During the main washing program, the system acquires the current water temperature data through a built-in temperature sensor at a fixed sampling period (e.g., every 5 seconds) and records it to form a time series: ;in, to This represents the time points from the start of the washing process to the completion of disinfection, where n represents the total number of time points. The system also records the target constant temperature value output by the disinfection response parameter model during this operation, denoted as . .

[0206] The system is based on the actual temperature of each sampling point. With target temperature The difference between them is used to calculate the instantaneous temperature deviation sequence: Subsequently, the deviation throughout the process was normalized and averaged to obtain the dynamic temperature deviation value ΔT_avg for this washing stage, denoted as: ΔT_avg is a quantitative evaluation index of the actual temperature control stability. The smaller the value, the higher the temperature control accuracy; the larger the value, the more frequent the fluctuations or control lag, which may affect the sterilization efficiency.

[0207] The specific steps for extracting and calculating the critical inhibition threshold of the target bacterial species are as follows:

[0208] After the fabric is washed and dried, the system collects residual bacterial data after this operation and identifies the survival status of the target bacterial species (from the pollution source information set G) in the post-wash residual sample through a biological detection module (such as rapid culture method, fluorescent staining count, or optional PCR rapid detection module).

[0209] Set a target bacterium before operation The initial bacterial load was: (Unit: CFU / mL);

[0210] After cleaning, the residual bacterial load was measured as follows: Then this operation will affect The actual suppression rate is defined as: For example: if the initial quantity is 10 6 If the concentration of CFU / mL is high and the residual concentration after washing is 10² CFU / mL, then the inhibition rate is:

[0211] ;

[0212] The system pre-sets recommended inhibition thresholds for each type of common multidrug-resistant bacteria, referred to as: For example, the threshold for MRSA is ≥ 99.99%; for Pseudomonas aeruginosa, it is ≥ 99.999%; and for Acinetobacter baumannii, it is ≥ 99.9%. The system will target each bacterium... The actual suppression rate is compared with the recommended threshold to form a difference. The expression is: ;

[0213] If the difference is negative, it means that the current program has not achieved the recommended sterilization effect; if it is positive, it indicates redundant disinfection and excessive resource consumption.

[0214] For all target bacterial species Perform a weighted average, taking into account the hazard level weight of each microbial species. The critical inhibition threshold of the target bacterial species was determined. : .

[0215] The dynamic temperature deviation value and the critical suppression threshold are converted into a comprehensive feature vector. The comprehensive feature vector is used as the input of the machine learning model. The machine learning model uses the error score label of the disinfection response parameter model for the control performance of this operation for each set of comprehensive feature vectors as the prediction objective. The training objective is to minimize the sum of the prediction errors of all disinfection response parameter models for the control performance of this operation. The machine learning model is trained until the sum of prediction errors converges and the model training stops. The error score value of the disinfection response parameter model for the control performance of this operation is determined according to the model output results. The machine learning model is a multinomial regression model.

[0216] When the error score E_model of the disinfection response parameter model for the control performance of this operation exceeds the set threshold E_thresh (e.g., 5.0), the system determines that there is a configuration deviation in the current model and triggers the automatic update logic.

[0217] The system will record the operation history of this batch (including...) Using (etc.) as new training samples, update the following model modules:

[0218] Adjust the weighting coefficients in the temperature response function to improve temperature control sensitivity;

[0219] The recommended disinfectant concentration C′ or contact time t′ should be adjusted downward or upward for the corresponding bacterial strain.

[0220] Refit the optimal temperature-concentration combination range for certain specific bacterial species.

[0221] By using gradient descent or incremental learning, only local regions of the model are corrected, preserving the overall stability of the model. New model versions are automatically archived, overwriting the original parameter tables.

[0222] After each correction operation is completed, the system records:

[0223] Original model parameters;

[0224] Actual operational feedback;

[0225] Correct the logical path;

[0226] New version number and activation time.

[0227] All historical model data supports backtracking analysis and fault comparison, ensuring the traceability and stability of the model evolution process.

[0228] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for operating a fabric cleaning and disinfection machine for controlling multidrug-resistant bacteria, characterized in that: include: S100: Obtain the pollution intensity level, fabric material type, and target bacterial species spectrum information of the target fabric, and construct the pollution source information set P; S200: Based on the pollution source information set P, call the preset disinfection response parameter model to determine the washing temperature T, washing and disinfection action time t, and disinfectant type and concentration parameter C; S300: Based on the fabric material type and its temperature and chemical resistance properties, retrieve the matching set of cleaning programs W from the washing machine database and dynamically adjust it according to disinfection requirements; The dynamic adjustment based on disinfection needs includes: Extract the washing temperature, washing and disinfection time, and disinfectant type and concentration output from the disinfection response parameter model; The standard programs that match the fabric material type in the preset cleaning program set are screened to form an initial candidate program set; Adjust the temperature rise curve, disinfection duration, and disinfectant injection timing in the initial candidate program according to the disinfection requirement level of the target bacterial species. Increase the program's set temperature without exceeding the fabric's temperature resistance limit; The frequency and rhythm of the rinsing process are dynamically adjusted to meet the requirements of different types of disinfectants for residue inhibition. The adjusted program parameters are combined to form the final running program, which is used to execute this fabric cleaning and disinfection task; S400: During the main washing program, it monitors changes in water temperature and detergent concentration in real time and adjusts washing parameters according to a preset feedback control model. The adjustment of washing parameters based on a preset feedback control model includes: A composite feedback control model incorporating fuzzy control and proportional-integral-derivative control is constructed, with the water temperature, detergent concentration, and disinfection time collected in real time during the washing process as input variables. Set target values ​​for washing parameters, including target water temperature, target detergent concentration, and desired disinfection time; Calculate the deviation between the current parameter and the target value, and determine the level of parameter deviation through the fuzzy inference module; Based on the deviation level, the corresponding adjustment command direction is output and input into the proportional-integral-derivative controller to generate a continuous control signal. The control signal is used to adjust the heater output, detergent dosing rate, stirring frequency, or washing stage time to dynamically correct deviations. S500: Extracts and analyzes the dynamic temperature deviation value during the washing stage of the washing and disinfection process and the critical inhibition threshold of the target bacteria species in the residual bacteria detection data, and automatically updates the disinfection response parameter model of fabric washing based on the analysis results.

2. The method for operating a fabric cleaning and disinfection machine for controlling multidrug-resistant bacteria according to claim 1, characterized in that: In S200, the disinfection response parameter model is a multivariate fitting model constructed based on a pollution source information set. The pollution source information set includes pollution intensity level, fabric material type, and target bacterial species spectrum information. The multivariate fitting model is constructed through the following steps: Historical fabric washing sample data were organized, and the pollution intensity level, fabric material type and target bacterial species spectrum information corresponding to each batch were extracted as input variables; Extract the actual operating parameters for the corresponding batch, including washing temperature, washing and disinfection time, and disinfectant type and concentration, as the target output variables; Multidimensional regression modeling was performed on the input and output data to construct a washing temperature prediction function, a time prediction function, and a disinfectant concentration recommendation function. In the modeling process, a tolerance adjustment mechanism and a weighting factor are introduced to control the acceptable fluctuation range of temperature, time and disinfectant concentration and the weighting influence of each input variable, respectively. Cross-validation and error feedback correction are performed on the model results to achieve dynamic adaptation of disinfection response parameters.

3. The method for operating a fabric cleaning and disinfection machine for controlling multidrug-resistant bacteria according to claim 1, characterized in that: In S500, the calculation steps for dynamic temperature deviation include: During the main washing process, the current water temperature data is acquired at a fixed sampling period and recorded to form a time series: ;in, to This represents the time points from the start of washing to the completion of disinfection, where n represents the total number of time points; it also records the target constant temperature value output by the disinfection response parameter model during this operation, denoted as . ; Based on the actual temperature of each sampling point With target temperature The difference between them is used to calculate the instantaneous temperature deviation sequence. : Subsequently, the deviation throughout the process was normalized and averaged to obtain the dynamic temperature deviation value ΔT_avg for this washing stage, denoted as: .

4. The method for operating a fabric cleaning and disinfection machine for controlling multidrug-resistant bacteria according to claim 3, characterized in that: The calculation steps for the critical inhibition threshold of the target bacterial species are as follows: After the fabric washing and drying are completed, residual bacterial data are collected after this operation, and the survival status of the target bacterial species in the residual samples after washing is identified. Set a target bacterium before operation The initial bacterial load was ; After washing, the residual bacterial load was measured to be... Then this operation will affect The actual suppression rate is defined as: ; Pre-set recommended inhibition thresholds for each type of common multidrug-resistant bacteria. ; each target bacterium The actual suppression rate is compared with the recommended threshold to form a difference. The expression is: ; For all target bacterial species By performing a weighted average and combining the hazard level weights of each bacterial species, the critical inhibition threshold of the target bacterial species is obtained.

5. The method for operating a fabric cleaning and disinfection machine for controlling multidrug-resistant bacteria according to claim 4, characterized in that: The dynamic temperature deviation value and the critical suppression threshold are converted into a comprehensive feature vector. The comprehensive feature vector is used as the input of the machine learning model. The machine learning model uses the error score label of the disinfection response parameter model for the control performance of this operation for each set of comprehensive feature vectors as the prediction objective. The training objective is to minimize the sum of the prediction errors of all the disinfection response parameter models for the control performance of this operation. The machine learning model is trained until the sum of prediction errors converges and the model training stops. The error score value of the disinfection response parameter model for the control performance of this operation is determined according to the model output results. The machine learning model is a multinomial regression model.

6. The method for operating a fabric cleaning and disinfection machine for controlling multidrug-resistant bacteria according to claim 5, characterized in that: When the error score E_model of the disinfection response parameter model for the control performance of this operation exceeds the set threshold E_thresh, it is determined that there is a configuration deviation in the disinfection response parameter model, and the automatic update logic is triggered.

Images