# PMSM_PM_Temp_Predict
PMSM_PM_Temp_Predict is a project aimed at predicting the temperature of the permanent magnet in a Permanent Magnet Synchronous Motor (PMSM). The temperature of the permanent magnet is an important parameter that affects the performance and reliability of the motor
## Description
This project utilizes machine learning techniques to develop a predictive model for estimating the temperature of the permanent magnet in a PMSM. The model takes into account various input parameters such as motor operating conditions, electrical voltages and currents, and environmental factors to make accurate temperature predictions. More specifically: the Random Forest Regressor is used for this project.
## Features
- API integration: The project provides an API that exposes the trained model, allowing other applications or systems to make temperature predictions programmatically
- Feature scaling: input data is normalized to meet regression model requirements
- Single sample processing: API contains the function to predict single temperature value based on current motor state
- Data frame processing: API allows you to process `pandas` `DataFrame` and get results for a huge amount of samples with one function call.
## Getting Started
To get started with the PMSM_PM_Temp_Predict project, follow these simple steps:
1. Install package with
`pip install pmsm-pm-temp-predict`
This command will install this python package and all required dependencies.
2. Integrate the trained model into your application using the provided API
3. Start making temperature predictions using the API and your collected data
For detailed instructions and usage examples, please refer to the documentation included in the repository.
## Contributing
Contributions to the PMSM_PM_Temp_Predict project are welcome. If you encounter any issues or have suggestions for improvements, please open an issue in the repository or submit a pull request with your proposed changes.
## API
Two functions are provided by API of this package:
### Single sample processing
`temp_predict`(`u_q, u_d, i_d, i_q, coolant, stator_winding`)
| parameter | type | description |
| ------ | ------ | ------ |
| `u_q` | `float` | q-component of the motor voltage in V |
| `u_d` | `float` | d-component of motor voltage in V |
| `i_d` | `float` | q-component of the motor current in A |
| `i_q` | `float` | d-component of the motor current in A |
| `coolant` | `float` | coolant temperature in В°C |
| `stator_winding` | `float` | stator winding temperature in В°C |
`return value` is a single `float` value which represents predicted temperature of the motor's permanent magnet.
#### Code example
```sh
import pmsm_pm_temp_predict as pms
print("Predicted permanent magnet temperature is: ", temp_predict(-0.450682,
-0.350055,
0.004419,
0.000328,
18.805172,
19.086670))
```
```sh
Output: Predicted permanent magnet temperature is: 24.849657903061008
```
### `DataFrame` processing
`temp_predict_df`(`df`)
| parameter | type | description |
| ------ | ------ | ------ |
| `df` | `pandas DataFrame` | a pandas DataFrame object containing columns similar to the parameters of the temp_predict function |
`return value` is an `array` of predicted temperatures of the motor's permanent magnet.
#### Code example
```sh
import pmsm_pm_temp_predict as pms
print("Predicted permanent magnet temperature is: ", temp_predict(-0.450682,
-0.350055,
0.004419,
0.000328,
18.805172,
19.086670))
print("Predicted permanent magnet temperature is: ", temp_predict_df(pd.DataFrame({'coolant': [18.805172],
'stator_winding': [19.086670],
'u_q': [-0.450682],
'u_d': [-0.350055],
'i_d': [0.004419],
'i_q': [0.000328]})))
```
```sh
Output: Predicted permanent magnet temperature is: [24.8496579]
```
Raw data
{
"_id": null,
"home_page": "",
"name": "pmsm-pm-temp-predict",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "python,pmsm,motor,temperatue,prediction",
"author": "Oleksandr",
"author_email": "<oleksandr.ohlashennyi.knm.2020@lpnu.ua>",
"download_url": "https://files.pythonhosted.org/packages/df/4f/393f64d65c8feb5fd124f988b37a413d7eb929d2213e1a6f0a6d73a7d33e/pmsm_pm_temp_predict-0.0.6.tar.gz",
"platform": null,
"description": "# PMSM_PM_Temp_Predict\nPMSM_PM_Temp_Predict is a project aimed at predicting the temperature of the permanent magnet in a Permanent Magnet Synchronous Motor (PMSM). The temperature of the permanent magnet is an important parameter that affects the performance and reliability of the motor\n\n## Description\nThis project utilizes machine learning techniques to develop a predictive model for estimating the temperature of the permanent magnet in a PMSM. The model takes into account various input parameters such as motor operating conditions, electrical voltages and currents, and environmental factors to make accurate temperature predictions. More specifically: the Random Forest Regressor is used for this project.\n\n## Features\n\n- API integration: The project provides an API that exposes the trained model, allowing other applications or systems to make temperature predictions programmatically\n- Feature scaling: input data is normalized to meet regression model requirements\n- Single sample processing: API contains the function to predict single temperature value based on current motor state\n- Data frame processing: API allows you to process `pandas` `DataFrame` and get results for a huge amount of samples with one function call.\n\n## Getting Started\n\nTo get started with the PMSM_PM_Temp_Predict project, follow these simple steps:\n\n1. Install package with \n`pip install pmsm-pm-temp-predict` \nThis command will install this python package and all required dependencies.\n2. Integrate the trained model into your application using the provided API\n3. Start making temperature predictions using the API and your collected data\n\nFor detailed instructions and usage examples, please refer to the documentation included in the repository.\n\n## Contributing\n\nContributions to the PMSM_PM_Temp_Predict project are welcome. If you encounter any issues or have suggestions for improvements, please open an issue in the repository or submit a pull request with your proposed changes.\n\n## API\n\nTwo functions are provided by API of this package:\n\n### Single sample processing\n`temp_predict`(`u_q, u_d, i_d, i_q, coolant, stator_winding`)\n\n| parameter | type | description |\n| ------ | ------ | ------ |\n| `u_q` | `float` | q-component of the motor voltage in V |\n| `u_d` | `float` | d-component of motor voltage in V |\n| `i_d` | `float` | q-component of the motor current in A |\n| `i_q` | `float` | d-component of the motor current in A |\n| `coolant` | `float` | coolant temperature in \u0412\u00b0C |\n| `stator_winding` | `float` | stator winding temperature in \u0412\u00b0C |\n\n`return value` is a single `float` value which represents predicted temperature of the motor's permanent magnet.\n\n#### Code example\n```sh\nimport pmsm_pm_temp_predict as pms\nprint(\"Predicted permanent magnet temperature is: \", temp_predict(-0.450682,\n -0.350055,\n 0.004419,\n 0.000328,\n 18.805172,\n 19.086670))\n```\n```sh\nOutput: Predicted permanent magnet temperature is: 24.849657903061008\n```\n\n\n### `DataFrame` processing\n\n`temp_predict_df`(`df`)\n\n| parameter | type | description |\n| ------ | ------ | ------ |\n| `df` | `pandas DataFrame` | a pandas DataFrame object containing columns similar to the parameters of the temp_predict function |\n\n`return value` is an `array` of predicted temperatures of the motor's permanent magnet.\n\n#### Code example\n```sh\nimport pmsm_pm_temp_predict as pms\nprint(\"Predicted permanent magnet temperature is: \", temp_predict(-0.450682,\n -0.350055,\n 0.004419,\n 0.000328,\n 18.805172,\n 19.086670))\n\nprint(\"Predicted permanent magnet temperature is: \", temp_predict_df(pd.DataFrame({'coolant': [18.805172], \n 'stator_winding': [19.086670],\n 'u_q': [-0.450682],\n 'u_d': [-0.350055],\n 'i_d': [0.004419],\n 'i_q': [0.000328]})))\n```\n```sh\nOutput: Predicted permanent magnet temperature is: [24.8496579]\n```\n\n\n",
"bugtrack_url": null,
"license": "",
"summary": "Permanent magnet temperature prediction",
"version": "0.0.6",
"project_urls": null,
"split_keywords": [
"python",
"pmsm",
"motor",
"temperatue",
"prediction"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f44348739ea3e30d5676c99b4eecc803dc8649108fec7b4f79f2d402d289188d",
"md5": "6f1a143188e11a74a0fe7900bbe5e8f8",
"sha256": "5a2bdb68c1a12fbff6564e137826830f2872c67ae8c958e7cd3af9a602bd9c94"
},
"downloads": -1,
"filename": "pmsm_pm_temp_predict-0.0.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6f1a143188e11a74a0fe7900bbe5e8f8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 4777,
"upload_time": "2023-06-11T22:37:05",
"upload_time_iso_8601": "2023-06-11T22:37:05.082607Z",
"url": "https://files.pythonhosted.org/packages/f4/43/48739ea3e30d5676c99b4eecc803dc8649108fec7b4f79f2d402d289188d/pmsm_pm_temp_predict-0.0.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "df4f393f64d65c8feb5fd124f988b37a413d7eb929d2213e1a6f0a6d73a7d33e",
"md5": "5567c950f62ef50ae2b3bce70e900c9c",
"sha256": "ace0039459e4df7997af9067718cad08b60252a8e2b480580c7bfade9d33a9e7"
},
"downloads": -1,
"filename": "pmsm_pm_temp_predict-0.0.6.tar.gz",
"has_sig": false,
"md5_digest": "5567c950f62ef50ae2b3bce70e900c9c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 3154,
"upload_time": "2023-06-11T22:37:07",
"upload_time_iso_8601": "2023-06-11T22:37:07.127464Z",
"url": "https://files.pythonhosted.org/packages/df/4f/393f64d65c8feb5fd124f988b37a413d7eb929d2213e1a6f0a6d73a7d33e/pmsm_pm_temp_predict-0.0.6.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-06-11 22:37:07",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "pmsm-pm-temp-predict"
}
JSON